ICCV 2025 Events with Videos

Posters

• IRGPT: Understanding Real-world Infrared Image with Bi-cross-modal Curriculum on Large-scale Benchmark
• VSP: Diagnosing the Dual Challenges of Perception and Reasoning in Spatial Planning Tasks for MLLMs
• VALLR: Visual ASR Language Model for Lip Reading
• Boosting Adversarial Transferability via Residual Perturbation Attack
• MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models
• Open-set Cross Modal Generalization via Multimodal Unified Representation
• FedWSQ: Efficient Federated Learning with Weight Standardization and Distribution-Aware Non-Uniform Quantization
• Dataset Distillation via Vision-Language Category Prototype
• Adversarial Training for Probabilistic Robustness
• AVTrustBench: Assessing and Enhancing Reliability and Robustness in Audio-Visual LLMs
• 2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining
• Backdoor Defense via Enhanced Splitting and Trap Isolation
• Diagnosing Pretrained Models for Out-of-distribution Detection
• ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models
• PAN-Crafter: Learning Modality-Consistent Alignment for PAN-Sharpening
• LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement
• Flexi-FSCIL: Adaptive Knowledge Retention for Breaking the Stability-Plasticity Dilemma in Few-Shot Class-Incremental Learning
• Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness
• Causal Disentanglement and Cross-Modal Alignment for Enhanced Few-Shot Learning
• FedPall: Prototype-based Adversarial and Collaborative Learning for Federated Learning with Feature Drift
• Visual Modality Prompt for Adapting Vision-Language Object Detectors
• Moderating the Generalization of Score-based Generative Model
• On the Complexity-Faithfulness Trade-off of Gradient-Based Explanations
• VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
• One Encoder to Rule them All: Representation Learning for Model-free Visual Reinforcement Learning using Fourier Neural Operators
• VisNumBench: Evaluating Number Sense of Multimodal Large Language Models
• Scaling and Taming Adversarial Training with Synthetic Data
• ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
• Mitigating Catastrophic Overfitting in Fast Adversarial Training via Label Information Elimination
• From Easy to Hard: Progressive Active Learning Framework for Infrared Small Target Detection with Single Point Supervision
• R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
• Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
• Zeroth-Order Fine-Tuning of LLMs in Random Subspaces
• Federated Representation Angle Learning
• TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning
• Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLMs
• Learning to Inference Adaptively for Multimodal Large Language Models
• Diffusion Guided Adaptive Augmentation for Generalization in Visual Reinforcement Learning
• A Linear N-Point Solver for Structure and Motion from Asynchronous Tracks
• NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
• Can Knowledge be Transferred from Unimodal to Multimodal? Investigating the Transitivity of Multimodal Knowledge Editing
• SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models
• DuET: Dual Incremental Object Detection via Exemplar-Free Task Arithmetic
• RANKCLIP: Ranking-Consistent Language-Image Pretraining
• Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models
• Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens
• TRNAS: A Training-Free Robust Neural Architecture Search
• ConstStyle: Robust Domain Generalization with Unified Style Transformation
• Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
• Visual Intention Grounding for Egocentric Assistants
• MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI
• Understanding Museum Exhibits using Vision-Language Reasoning
• Seal Your Backdoor with Variational Defense
• FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection
• SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
• RIPE: Reinforcement Learning on Unlabeled Image Pairs for Robust Keypoint Extraction
• CoST: Efficient Collaborative Perception From Unified Spatiotemporal Perspective
• G2D: Boosting Multimodal Learning with Gradient-Guided Distillation
• Removing Cost Volumes from Optical Flow Estimators
• Towards Effective Foundation Model Adaptation for Extreme Cross-Domain Few-Shot Learning
• BATCLIP: Bimodal Online Test-Time Adaptation for CLIP
• Controlling Multimodal LLMs via Reward-guided Decoding
• Boundary Probing for Input Privacy Protection When Using LMM Services
• TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
• Rethinking Few Shot CLIP Benchmarks: A Critical Analysis in the Inductive Setting
• EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients
• Auxiliary Prompt Tuning of Vision-Language Models for Few-Shot Out-of-Distribution Detection
• I Am Big, You Are Little; I Am Right, You Are Wrong
• KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles
• Token Activation Map to Visually Explain Multimodal LLMs
• DisCoPatch: Taming Adversarially-driven Batch Statistics for Improved Out-of-Distribution Detection
• Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection
• Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
• Is Visual in-Context Learning for Compositional Medical Tasks within Reach?
• MMOne: Representing Multiple Modalities in One Scene
• Class-Wise Federated Averaging for Efficient Personalization
• DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning
• Cooperative Pseudo Labeling for Unsupervised Federated Classification
• Adaptive Prompt Learning via Gaussian Outlier Synthesis for Out-of-distribution Detection
• Knowledge Distillation with Refined Logits
• Hypergraph Clustering Network with Partial Attribute Imputation
• Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
• Doodle Your Keypoints: Sketch-Based Few-Shot Keypoint Detection
• Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
• A Tiny Change, A Giant Leap: Long-Tailed Class-Incremental Learning via Geometric Prototype Alignment
• Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints
• SplatTalk: 3D VQA with Gaussian Splatting
• A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention
• GenieBlue: Integrating both Linguistic and Multimodal Capabilities for Large Language Models on Mobile Devices
• LIFT: Latent Implicit Functions for Task- and Data-Agnostic Encoding
• AIRA: Activation-Informed Low-Rank Adaptation for Large Models
• Effective Training Data Synthesis for Improving MLLM Chart Understanding
• Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
• Perspective-Aware Teaching: Adapting Knowledge for Heterogeneous Distillation
• FREE-Merging: Fourier Transform for Efficient Model Merging
• DAP-MAE: Domain-Adaptive Point Cloud Masked Autoencoder for Effective Cross-Domain Learning
• Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data
• LIRA: Reasoning Reconstruction via Multimodal Large Language Models
• CA2C: A Prior-Knowledge-Free Approach for Robust Label Noise Learning via Asymmetric Co-learning and Co-training
• PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection
• Learnable Logit Adjustment for Imbalanced Semi-Supervised Learning under Class Distribution Mismatch
• Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark
• GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability
• A Conditional Probability Framework for Compositional Zero-shot Learning
• Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning
• SMP-Attack: Boosting the Transferability of Feature Importance-based Adversarial Attack with Semantics-aware Multi-granularity Patchout
• Towards Real Unsupervised Anomaly Detection Via Confident Meta-Learning
• Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning
• FinMMR: Make Financial Numerical Reasoning More Multimodal, Comprehensive, and Challenging
• SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation
• DOGR: Towards Versatile Visual Document Grounding and Referring
• INTER: Mitigating Hallucination in Large Vision-Language Models by Interaction Guidance Sampling
• DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion
• What to Distill? Fast Knowledge Distillation with Adaptive Sampling
• Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understanding
• Spatial Preference Rewarding for MLLMs Spatial Understanding
• Joint Asymmetric Loss for Learning with Noisy Labels
• MissRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models
• Robust Dataset Condensation using Supervised Contrastive Learning
• Understanding Flatness in Generative Models: Its Role and Benefits
• From Easy to Hard: The MIR Benchmark for Progressive Interleaved Multi-Image Reasoning
• SAFER: Sharpness Aware layer-selective Finetuning for Enhanced Robustness in vision transformers
• DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
• BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes
• Tensor-aggregated LoRA in Federated Fine-tuning
• Category-Specific Selective Feature Enhancement for Long-Tailed Multi-Label Image Classification
• Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
• Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
• Gaze-Language Alignment for Zero-Shot Prediction of Visual Search Targets from Human Gaze Scanpaths
• Diversity-Enhanced Distribution Alignment for Dataset Distillation
• COSTARR: Consolidated Open Set Technique with Attenuation for Robust Recognition
• Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning
• SMSTracker: Tri-path Score Mask Sigma Fusion for Multi-Modal Tracking
• Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
• FEVER-OOD: Free Energy Vulnerability Elimination for Robust Out-of-Distribution Detection
• AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting
• Activation Subspaces for Out-of-Distribution Detection
• Evidential Knowledge Distillation
• Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning
• Noise-Modeled Diffusion Models for Low-Light Spike Image Restoration
• Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
• Enhancing Numerical Prediction of MLLMs with Soft Labeling
• Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models
• PEFTDiff: Diffusion-Guided Transferability Estimation for Parameter-Efficient Fine-Tuning
• Towards Privacy-preserved Pre-training of Remote Sensing Foundation Models with Federated Mutual-guidance Learning
• Gradient Extrapolation for Debiased Representation Learning
• VehicleMAE: View-asymmetry Mutual Learning for Vehicle Re-identification Pre-training via Masked AutoEncoders
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks
• PHD: Personalized 3D Human Body Fitting with Point Diffusion
• BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimation
• Princeton365: A Diverse Dataset with Accurate Camera Pose
• PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
• Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
• WildSAT: Learning Satellite Image Representations from Wildlife Observations
• DRaM-LHM: A Quaternion Framework for Iterative Camera Pose Estimation
• RoboTron-Nav: A Unified Framework for Embodied Navigation Integrating Perception, Planning, and Prediction
• Do It Yourself: Learning Semantic Correspondence from Pseudo-Labels
• Zero-shot Inexact CAD Model Alignment from a Single Image
• Find Any Part in 3D
• Beyond Pixel Uncertainty: Bounding the OoD Objects in Road Scenes
• Online Dense Point Tracking with Streaming Memory
• C4D: 4D Made from 3D through Dual Correspondences
• PoseSyn: Synthesizing Diverse 3D Pose Data from In-the-Wild 2D Data
• Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding
• Bring Your Rear Cameras for Egocentric 3D Human Pose Estimation
• SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting
• Combinative Matching for Geometric Shape Assembly
• CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Image
• MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation
• Training-Free Personalization via Retrieval and Reasoning on Fingerprints
• WildSeg3D: Segment Any 3D Objects in the Wild from 2D Images
• SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image
• Layer-wise Vision Injection with Disentangled Attention for Efficient LVLMs
• EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds
• Rethinking the Upsampling Process in Light Field Super-Resolution with Spatial-Epipolar Implicit Image Function
• From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras
• 4DSegStreamer: Streaming 4D Panoptic Segmentation via Dual Threads
• RoMo: Robust Motion Segmentation Improves Structure from Motion
• CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detector
• EMatch: A Unified Framework for Event-based Optical Flow and Stereo Matching
• MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
• Open-Vocabulary Octree-Graph for 3D Scene Understanding
• TESPEC: Temporally-Enhanced Self-Supervised Pretraining for Event Cameras
• Boosting Multi-View Indoor 3D Object Detection via Adaptive 3D Volume Construction
• VPR-Cloak: A First Look at Privacy Cloak Against Visual Place Recognition
• CoA-VLA: Improving Vision-Language-Action Models via Visual-Text Chain-of-Affordance
• AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
• From Abyssal Darkness to Blinding Glare: A Benchmark on Extreme Exposure Correction in Real World
• Learning to See Inside Opaque Liquid Containers using Speckle Vibrometry
• RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
• ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
• HoliTracer: Holistic Vectorization of Geographic Objects from Large-Size Remote Sensing Imagery
• Balanced Sharpness-Aware Minimization for Imbalanced Regression
• PHATNet: A Physics-guided Haze Transfer Network for Domain-adaptive Real-world Image Dehazing
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification
• Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
• DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstruction
• Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space
• Self-supervised Learning of Hybrid Part-aware 3D Representations of 2D Gaussians and Superquadrics
• CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation
• Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis
• GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
• Frequency Domain-Based Diffusion Model for Unpaired Image Dehazing
• Active Learning Meets Foundation Models: Fast Remote Sensing Data Annotation for Object Detection
• Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians
• FedVLA: Federated Vision-Language-Action Learning with Dual Gating Mixture-of-Experts for Robotic Manipulation
• Tracking Tiny Drones against Clutter: Large-Scale Infrared Benchmark with Motion-Centric Adaptive Algorithm
• CityNav: A Large-Scale Dataset for Real-World Aerial Navigation
• Heavy Labels Out! Dataset Distillation with Label Space Lightening
• VLM4D: Towards Spatiotemporal Awareness in Vision Language Models
• PRE-Mamba: A 4D State Space Model for Ultra-High-Frequent Event Camera Deraining
• Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
• SAC-GNC: SAmple Consensus for adaptive Graduated Non-Convexity
• Breaking Rectangular Shackles: Cross-View Object Segmentation for Fine-Grained Object Geo-Localization
• DAViD: Data-efficient and Accurate Vision Models from Synthetic Data
• BlinkTrack: Feature Tracking over 80 FPS via Events and Images
• Exploiting Frequency Dynamics for Enhanced Multimodal Event-based Action Recognition
• GLEAM: Learning Generalizable Exploration Policy for Active Mapping in Complex 3D Indoor Scene
• IGL-Nav: Incremental 3D Gaussian Localization for Image-goal Navigation
• Multi-view Gaze Target Estimation
• Robust Low-light Scene Restoration via Illumination Transition
• Task-Decoupled Bézier Surface Constraint for Uneven Low-Light Image Enhancement
• GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
• PS-Mamba: Spatial-Temporal Graph Mamba for Pose Sequence Refinement
• VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving
• Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints
• Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
• UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI
• Bridging the Sky and Ground: Towards View-Invariant Feature Learning for Aerial-Ground Person Re-Identification
• Generative Zoo
• Predict-Optimize-Distill: A Self-Improving Cycle for 4D Object Understanding
• AdaDrive: Self-Adaptive Slow-Fast System for Language-Grounded Autonomous Driving
• Is Tracking really more challenging in First Person Egocentric Vision?
• PlaneRAS: Learning Planar Primitives for 3D Plane Recovery
• O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views
• MonoFusion: Sparse-View 4D Reconstruction via Monocular Fusion
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy
• MeasureXpert: Automatic Anthropometric Measurement Extraction from Two Unregistered, Partial, Posed, and Dressed Body Scans
• Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
• Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
• MVGBench: a Comprehensive Benchmark for Multi-view Generation Models
• High-Resolution Spatiotemporal Modeling with Global-Local State Space Models for Video-Based Human Pose Estimation
• On the Generalization of Representation Uncertainty in Earth Observation
• Contact-Aware Amodal Completion for Human-Object Interaction via Multi-Regional Inpainting
• Met2Net: A Decoupled Two-Stage Spatio-Temporal Forecasting Model for Complex Meteorological Systems
• egoPPG: Heart Rate Estimation from Eye-Tracking Cameras in Egocentric Systems to Benefit Downstream Vision Tasks
• TriDi: Trilateral Diffusion of 3D Humans, Objects, and Interactions
• 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
• OV3D-CG: Open-vocabulary 3D Instance Segmentation with Contextual Guidance
• VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions
• St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World
• Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images
• Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering
• INS-MMBench: A Comprehensive Benchmark for Evaluating LVLMs' Performance in Insurance
• Time-Aware Auto White Balance in Mobile Photography
• CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy
• PBFG: A New Physically-Based Dataset and Removal of Lens Flares and Glares
• GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
• 3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding
• Diffusion-Based Extreme High-speed Scenes Reconstruction with the Complementary Vision Sensor
• Rethinking the Embodied Gap in Vision-and-Language Navigation: A Holistic Study of Physical and Visual Disparities
• UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence
• WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions
• EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision
• Hyper-Depth: Hypergraph-based Multi-Scale Representation Fusion for Monocular Depth Estimation
• Dark-ISP: Enhancing RAW Image Processing for Low-Light Object Detection
• Learning 3D Scene Analogies with Neural Contextual Scene Maps
• NavMorph: A Self-Evolving World Model for Vision-and-Language Navigation in Continuous Environments
• AgroBench: Vision-Language Model Benchmark in Agriculture
• Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras
• EquiCaps: Predictor-Free Pose-Aware Pre-Trained Capsule Networks
• VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting
• Future-Aware Interaction Network For Motion Forecasting
• PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization
• UMDATrack: Unified Multi-Domain Adaptive Tracking Under Adverse Weather Conditions
• Aether: Geometric-Aware Unified World Modeling
• Power of Cooperative Supervision: Multiple Teachers Framework for Advanced 3D Semi-Supervised Object Detection
• Where am I? Cross-View Geo-localization with Natural Language Descriptions
• LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes
• MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation
• Manual-PA: Learning 3D Part Assembly from Instruction Diagrams
• OVA-Fields: Weakly Supervised Open-Vocabulary Affordance Fields for Robot Operational Part Detection
• Single-Scanline Relative Pose Estimation for Rolling Shutter Cameras
• Multispectral Demosaicing via Dual Cameras
• A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba
• Not All Frame Features Are Equal: Video-to-4D Generation via Decoupling Dynamic-Static Features
• Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models
• Selective Contrastive Learning for Weakly Supervised Affordance Grounding
• Beyond RGB: Adaptive Parallel Processing for RAW Object Detection
• MonoMobility: Zero-Shot 3D Mobility Analysis from Monocular Videos
• PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation
• Variance-Based Pruning for Accelerating and Compressing Trained Networks
• Test-Time Retrieval-Augmented Adaptation for Vision-Language Models
• MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
• PLMP - Point-Line Minimal Problems for Projective SfM
• DCHM: Depth-Consistent Human Modeling for Multiview Detection
• STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?
• CAD-Assistant: Tool-Augmented VLLMs as Generic CAD Task Solvers
• OpenM3D: Open Vocabulary Multi-view Indoor 3D Object Detection without Human Annotations
• Weakly-Supervised Learning of Dense Functional Correspondences
• InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes
• ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness
• Voyaging into Perpetual Dynamic Scenes from a Single View
• Dynamic Reconstruction of Hand-Object Interaction with Distributed Force-aware Contact Representation
• Learnable Feature Patches and Vectors for Boosting Low-light Image Enhancement without External Knowledge
• Language Driven Occupancy Prediction
• Enhanced Event-based Dense Stereo via Cross-Sensor Knowledge Distillation
• M-SpecGene: Generalized Foundation Model for RGBT Multispectral Vision
• ReassembleNet: Learnable Keypoints and Diffusion for 2D Fresco Reconstruction
• PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image
• Optical Model-Driven Sharpness Mapping for Autofocus in Small Depth-of-Field and Severe Defocus Scenarios
• GSOT3D: Towards Generic 3D Single Object Tracking in the Wild
• Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle
• When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning
• ArgoTweak: Towards Self-Updating HD Maps through Structured Priors
• Revisiting Image Fusion for Multi-Illuminant White-Balance Correction
• Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints
• PseudoMapTrainer: Learning Online Mapping without HD Maps
• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training
• Quanta Neural Networks: From Photons to Perception
• PanSt3R: Multi-view Consistent Panoptic Segmentation
• Harnessing Input-Adaptive Inference for Efficient VLN
• Event-aided Dense and Continuous Point Tracking: Everywhere and Anytime
• Unlocking Constraints: Source-Free Occlusion-Aware Seamless Segmentation
• AnimalClue: Recognizing Animals by their Traces
• DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
• Reverse Convolution and Its Applications to Image Restoration
• MP-HSIR: A Multi-Prompt Framework for Universal Hyperspectral Image Restoration
• Bridging the Skeleton-Text Modality Gap: Diffusion-Powered Modality Alignment for Zero-shot Skeleton-based Action Recognition
• DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion
• PUMPS: Skeleton-Agnostic Point-based Universal Motion Pre-Training for Synthesis in Human Motion Tasks
• Animate Anyone 2: High-Fidelity Character Image Animation with Environment Affordance
• InfiniDreamer: Arbitrarily Long Human Motion Generation via Segment Score Distillation
• Blind Noisy Image Deblurring Using Residual Guidance Strategy
• V2M4: 4D Mesh Animation Reconstruction from a Single Monocular Video
• DisenQ: Disentangling Q-Former for Activity-Biometrics
• Sequential Gaussian Avatars with Hierarchical Motion Context
• MotionShot: Adaptive Motion Transfer across Arbitrary Objects for Text-to-Video Generation
• AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
• LayerAnimate: Layer-level Control for Animation
• Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis
• Dual-Temporal Exemplar Representation Network for Video Semantic Segmentation
• CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation
• SemGes: Semantics-aware Co-Speech Gesture Generation using Semantic Coherence and Relevance Learning
• PatchScaler: An Efficient Patch-Independent Diffusion Model for Image Super-Resolution
• AV-Flow: Transforming Text to Audio-Visual Human-like Interactions
• MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
• AU-Blendshape for Fine-grained Stylized 3D Facial Expression Manipulation
• Towards a Unified Copernicus Foundation Model for Earth Vision
• SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation
• SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis
• LongAnimation: Long Animation Generation with Dynamic Global-Local Memory
• VoluMe – Authentic 3D Video Calls from Live Gaussian Splat Prediction
• EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
• KinMo: Kinematic-aware Human Motion Understanding and Generation
• What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning
• FreeDance: Towards Harmonic Free-Number Group Dance Generation via a Unified Framework
• RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model
• Q-Norm: Robust Representation Learning via Quality-Adaptive Normalization
• FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads
• Bridging Class Imbalance and Partial Labeling via Spectral-Balanced Energy Propagation for Skeleton-based Action Recognition
• Beyond Walking: A Large-Scale Image-Text Benchmark for Text-based Person Anomaly Search
• PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning
• DGTalker: Disentangled Generative Latent Space Learning for Audio-Driven Gaussian Talking Heads
• Robust Test-Time Adaptation for Single Image Denoising Using Deep Gaussian Prior
• DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
• 2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos
• Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
• Highlight What You Want: Weakly-Supervised Instance-Level Controllable Infrared-Visible Image Fusion
• Weakly Supervised Visible-Infrared Person Re-Identification via Heterogeneous Expert Collaborative Consistency Learning
• DanceEditor: Towards Iterative Editable Music-driven Dance Generation with Open-Vocabulary Descriptions
• Human-Object Interaction from Human-Level Instructions
• Semantic Alignment and Reinforcement for Data-Free Quantization of Vision Transformers
• HOMO-Feature: Cross-Arbitrary-Modal Image Matching with Homomorphism of Organized Major Orientation
• Align Your Rhythm: Generating Highly Aligned Dance Poses with Gating-Enhanced Rhythm-Aware Feature Representation
• GUAVA: Generalizable Upper Body 3D Gaussian Avatar
• InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
• Generic Event Boundary Detection via Denoising Diffusion
• StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors
• UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control
• Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis
• Efficient Multi-Person Motion Prediction by Lightweight Spatial and Temporal Interactions
• PrimHOI: Compositional Human-Object Interaction via Reusable Primitives
• NullSwap: Proactive Identity Cloaking Against Deepfake Face Swapping
• Learning Pixel-adaptive Multi-layer Perceptrons for Real-time Image Enhancement
• LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning
• Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation
• UDC-VIT: A Real-World Video Dataset for Under-Display Cameras
• FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration
• Context-Aware Academic Emotion Dataset and Benchmark
• MotionLab: Unified Human Motion Generation and Editing via the Motion-Condition-Motion Paradigm
• Consistency Trajectory Matching for One-Step Generative Super-Resolution
• Learning Precise Affordances from Egocentric Videos for Robotic Manipulation
• Autoregressive Denoising Score Matching is a Good Video Anomaly Detector
• DIMO: Diverse 3D Motion Generation for Arbitrary Objects
• Hierarchical-aware Orthogonal Disentanglement Framework for Fine-grained Skeleton-based Action Recognition
• iManip: Skill-Incremental Learning for Robotic Manipulation
• Exploiting Diffusion Prior for Task-driven Image Restoration
• Learning Efficient and Generalizable Human Representation with Human Gaussian Model
• Capturing head avatar with hand contacts from a monocular video
• The Source Image is the Best Attention for Infrared and Visible Image Fusion
• Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition
• EAMamba: Efficient All-Around Vision State Space Model for Image Restoration
• IM-LUT: Interpolation Mixing Look-Up Tables for Image Super-Resolution
• CarGait: Cross-Attention based Re-ranking for Gait recognition
• PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
• VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers
• Multi-modal Multi-platform Person Re-Identification: Benchmark and Method
• Learning Hierarchical Line Buffer for Image Processing
• GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation
• Multi-Object Sketch Animation by Scene Decomposition and Motion Planning
• FPEM: Face Prior Enhanced Facial Attractiveness Prediction for Live Videos with Face Retouching
• MotionDiff: Training-free Zero-shot Interactive Motion Editing via Flow-assisted Multi-view Diffusion
• LA-MOTR: End-to-End Multi-Object Tracking by Learnable Association
• Expressive Talking Human from Single-Image with Imperfect Priors
• MOVE: Motion-Guided Few-Shot Video Object Segmentation
• EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment
• Joint Self-Supervised Video Alignment and Action Segmentation
• SHeaP: Self-supervised Head Geometry Predictor Learned via 2D Gaussians
• Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection
• Separation for Better Integration: Disentangling Edge and Motion in Event-based Deblurring
• GMMamba: Group Masking Mamba for Whole Slide Image Classification
• DexVLG: Dexterous Vision-Language-Grasp Model at Scale
• EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
• EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception
• PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image
• Understanding Co-speech Gestures in-the-wild
• DreamRelation: Relation-Centric Video Customization
• MaskControl: Spatio-Temporal Control for Masked Motion Synthesis
• General Compression Framework for Efficient Transformer Object Tracking
• MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation
• Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection
• G-DexGrasp: Generalizable Dexterous Grasping Synthesis Via Part-Aware Prior Retrieval and Prior-Assisted Generation
• SyncDiff: Synchronized Motion Diffusion for Multi-Body Human-Object Interaction Synthesis
• Blind Video Super-Resolution based on Implicit Kernels
• SEREP: Semantic Facial Expression Representation for Robust In-the-Wild Capture and Retargeting
• SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
• VSRM: A Robust Mamba-Based Framework for Video Super-Resolution
• PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion
• Latent-Reframe: Enabling Camera Control for Video Diffusion Models without Training
• Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution
• RoboPearls: Editable Video Simulation for Robot Manipulation
• UniFuse: A Unified All-in-One Framework for Multi-Modal Medical Image Fusion Under Diverse Degradations and Misalignments
• F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration
• ChartCap: Mitigating Hallucination of Dense Chart Captioning
• Face Retouching with Diffusion Data Generation and Spectral Restorement
• UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization
• Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model
• Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
• GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar
• Skeleton Motion Words for Unsupervised Skeleton-based Temporal Action Segmentation
• CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
• Identity Preserving 3D Head Stylization with Multiview Score Distillation
• Towards a Universal Image Degradation Model via Content-Degradation Disentanglement
• Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking
• GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule
• AMDANet: Attention-Driven Multi-Perspective Discrepancy Alignment for RGB-Infrared Image Fusion and Segmentation
• DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing
• GaussianSpeech: Audio-Driven Personalized 3D Gaussian Avatars
• DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability
• OneGT: One-Shot Geometry-Texture Neural Rendering for Head Avatars
• Perception-as-Control: Fine-grained Controllable Image Animation with 3D-aware Motion Representation
• FineMotion: A Dataset and Benchmark with both Spatial and Temporal Annotation for Fine-grained Motion Generation and Editing
• TeRA: Rethinking Text-guided Realistic 3D Avatar Generation
• Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration
• DexH2R: A Benchmark for Dynamic Dexterous Grasping in Human-to-Robot Handover
• IDFace: Face Template Protection for Efficient and Secure Identification
• AdaHuman: Animatable Detailed 3D Human Generation with Compositional Multiview Diffusion
• MamTiff-CAD: Multi-Scale Latent Diffusion with Mamba+ for Complex Parametric Sequence
• Balancing Task-invariant Interaction and Task-specific Adaptation for Unified Image Fusion
• DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion
• Efficient Concertormer for Image Deblurring and Beyond
• Augmented Mass-Spring Model for Real-Time Dense Hair Simulation
• DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
• AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigm
• MagicID: Hybrid Preference Optimization for ID-Consistent and Dynamic-Preserved Video Customization
• MistSense: Versatile Online Detection of Procedural and Execution Mistakes
• Im2Haircut: Single-view Strand-based Hair Reconstruction for Human Avatars
• Efficient Track Anything
• ASCENT: Annotation-free Self-supervised Contrastive Embeddings for 3D Neuron Tracking in Fluorescence Microscopy
• VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models
• Controllable Weather Synthesis and Removal with Video Diffusion Models
• FED-PsyAU: Privacy-Preserving Micro-Expression Recognition via Psychological AU Coordination and Dynamic Facial Motion Modeling
• Self-Calibrated Variance-Stabilizing Transformations for Real-World Image Denoising
• LD-RPS: Zero-Shot Unified Image Restoration via Latent Diffusion Recurrent Posterior Sampling
• Multi-modal Identity Extraction
• Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars
• GazeGaussian: High-Fidelity Gaze Redirection with 3D Gaussian Splatting
• SVG-Head: Hybrid Surface-Volumetric Gaussians for High-Fidelity Head Reconstruction and Real-Time Editing
• SAMPLE: Semantic Alignment through Temporal-Adaptive Multimodal Prompt Learning for Event-Based Open-Vocabulary Action Recognition
• Rethinking Key-frame-based Micro-expression Recognition: A Robust and Accurate Framework Against Key-frame Errors
• Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions
• FlowStyler: Artistic Video Stylization via Transformation Fields Transports
• ZFusion: Efficient Deep Compositional Zero-shot Learning for Blind Image Super-Resolution with Generative Diffusion Prior
• MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization
• Vivid4D: Improving 4D Reconstruction from Monocular Video by Video Inpainting
• DisCoRD: Discrete Tokens to Continuous Motion via Rectified Flow Decoding
• Learning Streaming Video Representation via Multitask Training
• SegmentDreamer: Towards High-fidelity Text-to-3D Synthesis with Segmented Consistency Trajectory Distillation
• Textured 3D Regenerative Morphing with 3D Diffusion Prior
• Blended Point Cloud Diffusion for Localized Text-guided Shape Editing
• TCFG: Truncated Classifier-Free Guidance for Efficient and Scalable Text-to-Image Acceleration
• Versatile Transition Generation with Image-to-Video Diffusion
• AnyPortal: Zero-Shot Consistent Video Background Replacement
• UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
• TikZero: Zero-Shot Text-Guided Graphics Program Synthesis
• FiVE-Bench: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
• Tune-Your-Style: Intensity-tunable 3D Style Transfer with Gaussian Splatting
• Continual Personalization for Diffusion Models
• DiffSim: Taming Diffusion Models for Evaluating Visual Similarity
• DLF: Extreme Image Compression with Dual-generative Latent Fusion
• Streamlining Image Editing with Layered Diffusion Brushes
• PlugMark: A Plug-in Zero-Watermarking Framework for Diffusion Models
• DACoN: DINO for Anime Paint Bucket Colorization with Any Number of Reference Images
• DCT-Shield: A Robust Frequency Domain Defense against Malicious Image Editing
• Draw Your Mind: Personalized Generation via Condition-Level Modeling in Text-to-Image Diffusion Models
• PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models
• Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
• LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
• DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models
• Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation
• On Large Multimodal Models as Open-World Image Classifiers
• GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation
• FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Models
• Text Embedding Knows How to Quantize Text-Guided Diffusion Models
• Multi-turn Consistent Image Editing
• Deterministic Object Pose Confidence Region Estimation
• DIA: The Adversarial Exposure of Deterministic Inversion in Diffusion Models
• VACE: All-in-One Video Creation and Editing
• DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization
• Zero-Shot Depth Aware Image Editing with Diffusion Models
• Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics
• Modeling Human Gaze Behavior with Diffusion Models for Unified Scanpath Prediction
• MetaMorph: Multimodal Understanding and Generation via Instruction Tuning
• Certifiably Optimal Anisotropic Rotation Averaging
• Outlier-Aware Post-Training Quantization for Image Super-Resolution
• GReg: Geometry-Aware Region Refinement for Sign Language Video Generation
• SuMa: A Subspace Mapping Approach for Robust and Effective Concept Erasure in Text-to-Image Diffusion Models
• LUSD: Localized Update Score Distillation for Text-Guided Image Editing
• LoRA.rar: Learning to Merge LoRAs via Hypernetworks for Subject-Style Conditioned Image Generation
• SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting
• Make Me Happier: Evoking Emotions Through Image Diffusion Models
• Accelerating Diffusion Transformer via Gradient-Optimized Cache
• FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion
• DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
• Semantic Discrepancy-aware Detector for Image Forgery Identification
• Wasserstein Style Distribution Analysis and Transform for Stylized Image Generation
• CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models
• DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution
• CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models
• TokensGen: Harnessing Condensed Tokens for Long Video Generation
• Adaptive Caching for Faster Video Generation with Diffusion Transformers
• Region-Level Data Attribution for Text-to-Image Generative Models
• ART: Adaptive Relation Tuning for Generalized Relation Prediction
• PromptDresser: Improving the Quality and Controllability of Virtual Try-On via Generative Textual Prompt and Prompt-aware Mask
• Generative Adversarial Diffusion
• Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation
• Fine-Tuning Visual Autogressive Models for Subject-Driven Generation
• IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance
• Beyond Blur: A Fluid Perspective on Generative Diffusion Models
• Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis
• Training-free Geometric Image Editing on Diffusion Models
• PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation
• DDB: Diffusion Driven Balancing to Address Spurious Correlations
• V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models
• VSC: Visual Search Compositional Text-to-Image Diffusion Model
• Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization
• TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning In Text-to-Image Models
• From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition
• RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
• Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
• ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
• Beyond Perspective: Neural 360-Degree Video Compression
• Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention
• Colors See Colors Ignore: Clothes Changing ReID with Color Disentanglement
• From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
• Mobile Video Diffusion
• AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
• Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection
• Anti-Tamper Protection for Unauthorized Individual Image Generation
• StyleKeeper: Prevent Content Leakage using Negative Visual Query Guidance
• Scalable Image Tokenization with Index Backpropagation Quantization
• DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models
• DiffIP: Representation Fingerprints for Robust IP Protection of Diffusion Models
• TryOn-Refiner: Conditional Rectified-flow-based TryOn Refiner for More Accurate Detail Reconstruction
• Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation
• Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
• Learning Robust Image Watermarking with Lossless Cover Recovery
• FontAnimate: High Quality Few-shot Font Generation via Animating Font Transfer Process
• Frequency-Guided Diffusion for Training-Free Text-Driven Image Translation
• Neighboring Autoregressive Modeling for Efficient Visual Generation
• SummDiff: Generative Modeling of Video Summarization with Diffusion
• Generative Video Bi-flow
• Denoising Token Prediction in Masked Autoregressive Models
• SliderSpace: Decomposing the Visual Capabilities of Diffusion Models
• Rethink Sparse Signals for Pose-guided Text-to-image Generation
• Semantic Watermarking Reinvented: Enhancing Robustness and Generation Quality with Fourier Integrity
• CompleteMe: Reference-based Human Image Completion
• UnZipLoRA: Separating Content and Style from a Single Image
• ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation
• IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation
• EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model
• MaTe: Images Are All You Need for Material Transfer via Diffusion Transformer
• Translation of Text Embedding via Delta Vector to Suppress Strongly Entangled Content in Text-to-Image Diffusion Models
• VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
• Split-and-Combine: Enhancing Style Augmentation for Single Domain Generalization
• LACONIC: A 3D Layout Adapter for Controllable Image Creation
• Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis
• Progressive Artwork Outpainting via Latent Diffusion Models
• Edicho: Consistent Image Editing in the Wild
• DIVE: Taming DINO for Subject-Driven Video Editing
• Processing and acquisition traces in visual encoders: What does CLIP know about your camera?
• FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing
• Pretrained Reversible Generation as Unsupervised Visual Representation Learning
• CAP: Evaluation of Persuasive and Creative Image Generation
• Scale Your Instructions: Enhance the Instruction-Following Fidelity of Unified Image Generation Model by Self-Adaptive Attention Scaling
• Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
• Golden Noise for Diffusion Models: A Learning Framework
• Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues
• Dual-Expert Consistency Model for Efficient and High-Quality Video Generation
• VQ-SGen: A Vector Quantized Stroke Representation for Creative Sketch Generation
• Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
• OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
• DICE: Staleness-Centric Optimizations for Parallel Diffusion MoE Inference
• LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D Generation
• CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation
• LATINO-PRO: LAtent consisTency INverse sOlver with PRompt Optimization
• Text2Outfit: Controllable Outfit Generation with Multimodal Language Models
• ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection
• Spectral Image Tokenizer
• Magic Insert: Style-Aware Drag-and-Drop
• Forensic-MoE: Exploring Comprehensive Synthetic Image Detection Traces with Mixture of Experts
• Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
• PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs
• The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation
• LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
• DiffVSR: Revealing an Effective Recipe for Taming Robust Video Super-Resolution Against Complex Degradations
• GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography
• SDMatte: Grafting Diffusion Models for Interactive Matting
• Supercharged One-step Text-to-Image Diffusion Models with Negative Prompts
• LEGION: Learning to Ground and Explain for Synthetic Image Detection
• Photolithography Overlay Map Generation with Implicit Knowledge Distillation Diffusion Transformer
• IQA-Adapter: Exploring Knowledge Transfer from Image Quality Assessment to Diffusion-based Generative Models
• Preserve Anything: Controllable Image Synthesis with Object Preservation
• ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation
• Instruction-based Image Editing with Planning, Reasoning, and Generation
• Tracing Copied Pixels and Regularizing Patch Affinity in Copy Detection
• Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model
• MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment
• Spatial-Temporal Forgery Trace based Forgery Image Identification
• Few-Shot Pattern Detection via Template Matching and Regression
• Ensemble Foreground Management for Unsupervised Object Discovery
• Training-Free Industrial Defect Generation with Diffusion Models
• Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
• Aligning Moments in Time using Video Queries
• Counting Stacked Objects
• Robustifying Zero-Shot Vision Language Models by Subspaces Alignment
• Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes
• Adapt Foundational Segmentation Models with Heterogeneous Searching Space
• Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning
• ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection
• Fix-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text
• Task Vector Quantization for Memory-Efficient Model Merging
• COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation
• B-VLLM: A Vision Large Language Model with Balanced Spatio-Temporal Tokens
• Language Decoupling with Fine-grained Knowledge Guidance for Referring Multi-object Tracking
• CoHD: A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation
• ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba
• Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos
• LOTS of Fashion! Multi-Conditioning for Image Generation via Sketch-Text Pairing
• Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
• STDDNet: Harnessing Mamba for Video Polyp Segmentation via Spatial-aligned Temporal Modeling and Discriminative Dynamic Representation Learning
• GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices
• GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis
• LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
• ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis
• Visual Textualization for Image Prompted Object Detection
• Vision-Language Neural Graph Featurization for Extracting Retinal Lesions
• Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis
• ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail
• Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation
• UniDxMD: Towards Unified Representation for Cross-Modal Unsupervised Domain Adaptation in 3D Semantic Segmentation
• MA-CIR: A Multimodal Arithmetic Benchmark for Composed Image Retrieval
• Constructing Ophthalmic MLLM for Positioning-diagnosis Collaboration Through Clinical Cognitive Chain Reasoning
• SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
• MaskSAM: Auto-prompt SAM with Mask Classification for Volumetric Medical Image Segmentation
• ResQ: A Novel Framework to Implement Residual Neural Networks on Analog Rydberg Atom Quantum Computers
• MRGen: Segmentation Data Engine For Underrepresented MRI Modalities
• HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss
• HiERO: Understanding the Hierarchy of Human Behavior Enhances Reasoning on Egocentric Videos
• TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding
• Embodied Image Captioning: Self-supervised Learning Agents for Spatially Coherent Image Descriptions
• Toward Long-Tailed Online Anomaly Detection through Class-Agnostic Concepts
• OmniDiff: A Comprehensive Benchmark for Fine-grained Image Difference Captioning
• SIC: Similarity-Based Interpretable Image Classification with Neural Networks
• Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation
• ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation
• Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
• Sparse-Dense Side-Tuner for efficient Video Temporal Grounding
• CalliReader: Contextualizing Chinese Calligraphy via an Embedding-Aligned Vision-Language Model
• Music Grounding by Short Video
• PS3: A Multimodal Transformer Integrating Pathology Reports with Histology Images and Biological Pathways for Cancer Survival Prediction
• End-to-End Multi-Modal Diffusion Mamba
• Zero-Shot Composed Image Retrieval via Dual-Stream Instruction-Aware Distillation
• CNS-Bench: Benchmarking Image Classifier Robustness Under Continuous Nuisance Shifts
• CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation
• Soft Local Completeness: Rethinking Completeness in XAI
• Agreement aware and dissimilarity oriented GLOM
• MSA2: Multi-task Framework with Structure-aware and Style-adaptive Character Representation for Open-set Chinese Text Recognition
• Zero-Shot Compositional Video Learning with Coding Rate Reduction
• VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization
• CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition
• MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective
• MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing
• ViLLa: Video Reasoning Segmentation with Large Language Model
• Superpowering Open-Vocabulary Object Detectors for X-ray Vision
• TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision
• LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering
• Generalized Few-Shot Point Cloud Segmentation via LLM-Assisted Hyper-Relation Matching
• CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning
• Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation
• Rectifying Magnitude Neglect in Linear Attention
• Towards Omnimodal Expressions and Reasoning in Referring Audio-Visual Segmentation
• Identity-aware Language Gaussian Splatting for Open-vocabulary 3D Semantic Segmentation
• Graph Domain Adaptation with Dual-branch Encoder and Two-level Alignment for Whole Slide Image-based Survival Prediction
• Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers
• WeaveSeg: Iterative Contrast-weaving and Spectral Feature-refining for Nuclei Instance Segmentation
• Growing a Twig to Accelerate Large Vision-Language Models
• CountSE: Soft Exemplar Open-set Object Counting
• SignRep: Enhancing Self-Supervised Sign Representations
• D-Attn: Decomposed Attention for Large Vision-and-Language Model
• ProbMED: A Probabilistic Framework for Medical Multimodal Binding
• LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation
• Know Your Attention Maps: Class-specific Token Masking for Weakly Supervised Semantic Segmentation
• MEH: A Multi-Style Dataset and Toolkit for Advancing Egyptian Hieroglyph Recognition
• HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics
• ReferEverything: Towards Segmenting Everything We Can Speak of in Videos
• Prompt Guidance and Human Proximal Perception for HOT Prediction with Regional Joint Loss
• Object-centric Video Question Answering with Visual Grounding and Referring
• AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model
• Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
• Modeling Saliency Dataset Bias
• Enhancing Prompt Generation with Adaptive Refinement for Camouflaged Object Detection
• METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models
• RA-BUSSeg: Relation-aware Semi-supervised Breast Ultrasound Image Segmentation via Adjacent Propagation and Cross-layer Alignment
• AcZeroTS: Active Learning for Zero-shot Tissue Segmentation in Pathology Images
• LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
• Learn2Synth: Learning Optimal Data Synthesis Using Hypergradients for Brain Image Segmentation
• CABLD: Contrast-Agnostic Brain Landmark Detection with Consistency-Based Regularization
• Multi-modal Segment Anything Model for Camouflaged Scene Segmentation
• Memory-Efficient 4-bit Preconditioned Stochastic Optimization
• Temperature in Cosine-based Softmax Loss
• Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization
• MSQ: Memory-Efficient Bit Sparsification Quantization
• Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations
• NETracer: A Topology-Aware Iterative Tracing Approach for Tubular Structure Extraction
• The Devil is in the Spurious Correlations: Boosting Moment Retrieval with Dynamic Learning
• How Can Objects Help Video-Language Understanding?
• Efficient Fine-Tuning of Large Models via Nested Low-Rank Adaptation
• Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped Disentanglement
• Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations
• Is CLIP ideal? No. Can we fix it? Yes!
• Mind the Gap: Aligning Vision Foundation Models to Image Feature Matching
• Prior2Former - Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation
• G2PDiffusion: Cross-species Genotype-to-Phenotype Prediction via Evolutionary Diffusion
• Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences
• Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training
• Unified Open-World Segmentation with Multi-Modal Prompts
• UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation
• Prototypes are Balanced Units for Efficient and Effective Partially Relevant Video Retrieval
• LLM-enhanced Action-aware Multi-modal Prompt Tuning for Image-Text Matching
• Everything is a Video: Unifying Modalities through Next-Frame Prediction
• ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation
• Teaching AI the Anatomy Behind the Scan: Addressing Anatomical Flaws in Medical Image Segmentation with Learnable Prior
• C2MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
• MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning
• Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval
• PVChat: Personalized Video Chat with One-Shot Learning
• Adaptive Learning of High-Value Regions for Semi-Supervised Medical Image Segmentation
• CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
• MINERVA: Evaluating Complex Video Reasoning
• Lumina-Image 2.0: A Unified and Efficient Image Generative Framework
• Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation
• SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
• YOLOE: Real-Time Seeing Anything
• Incremental Few-Shot Semantic Segmentation via Multi-Level Switchable Visual Prompts
• Factorized Learning for Temporally Grounded Video-Language Models
• AURELIA: Test-time Reasoning Distillation in Audio-Visual LLMs
• Large-scale Pre-training for Grounded Video Caption Generation
• Neuroverse3D: Developing In-Context Learning Universal Model for Neuroimaging in 3D
• When Confidence Fails: Revisiting Pseudo-Label Selection in Semi-supervised Semantic Segmentation
• Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator
• Emulating Self-attention with Convolution for Efficient Image Super-Resolution
• RadGPT: Constructing 3D Image-Text Tumor Datasets
• When Pixel Difference Patterns Meet ViT: PiDiViT for Few-Shot Object Detection
• Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
• Auto-Vocabulary Semantic Segmentation
• Scheduling Weight Transitions for Quantization-Aware Training
• Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA
• Advancing Visual Large Language Model for Multi-granular Versatile Perception
• FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction
• 3DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardt
• Towards Visual Localization Interoperability: Cross-Feature for Collaborative Visual Localization and Mapping
• ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models
• OccluGaussian: Occlusion-Aware Gaussian Splatting for Large Scene Reconstruction and Rendering
• DoppDrive: Doppler-Driven Temporal Aggregation for Improved Radar Object Detection
• Unraveling the Effects of Synthetic Data on End-to-End Autonomous Driving
• HVPUNet: Hybrid-Voxel Point-cloud Upsampling Network
• GaussianUpdate: Continual 3D Gaussian Splatting Update for Changing Environments
• Robust and Efficient 3D Gaussian Splatting for Urban Scene Reconstruction
• Purge-Gate: Efficient Backpropagation-Free Test-Time Adaptation for Point Clouds via Token purging
• PriorMotion: Generative Class-Agnostic Motion Prediction with Raster-Vector Motion Field Priors
• RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
• M2EIT: Multi-Domain Mixture of Experts for Robust Neural Inertial Tracking
• GeoDistill: Geometry-Guided Self-Distillation for Weakly Supervised Cross-View Localization
• Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis
• IM360: Large-scale Indoor Mapping with 360 Cameras
• χ: Symmetry Understanding of 3D Shapes via Chirality Disentanglement
• Probabilistic Inertial Poser (ProbIP): Uncertainty-aware Human Motion Modeling from Sparse Inertial Sensors
• Uncertainty-Aware Diffusion-Guided Refinement of 3D Scenes
• Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
• Epona: Autoregressive Diffusion World Model for Autonomous Driving
• All in One: Visual-Description-Guided Unified Point Cloud Segmentation
• MiDSummer: Multi-Guidance Diffusion for Controllable Zero-Shot Immersive Gaussian Splatting Scene Generation
• FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging
• Unified Multi-Agent Trajectory Modeling with Masked Trajectory Diffusion
• Coordinate-based Speed of Sound Recovery for Aberration-Corrected Photoacoustic Computed Tomography
• Axis-level Symmetry Detection with Group-Equivariant Representation
• Monocular Semantic Scene Completion via Masked Recurrent Networks
• Controllable 3D Outdoor Scene Generation via Scene Graphs
• RESCUE: Crowd Evacuation Simulation via Controlling SDM-United Characters
• DAA*: Deep Angular A Star for Image-based Path Planning
• SurfaceSplat: Connecting Surface Reconstruction and Gaussian Splatting
• SU-RGS: Relightable 3D Gaussian Splatting from Sparse Views under Unconstrained Illuminations
• InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation
• PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model
• DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving
• Mixed Signals: A Diverse Point Cloud Dataset for Heterogeneous LiDAR V2X Collaboration
• Correspondence-Free Fast and Robust Spherical Point Pattern Registration
• Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmaps
• Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Ranging
• JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers
• CF3: Compact and Fast 3D Feature Fields
• 3DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Views
• SGAD: Semantic and Geometric-aware Descriptor for Local Feature Matching
• Decoupled Diffusion Sparks Adaptive Scene Generation
• Focal Plane Visual Feature Generation and Matching on a Pixel Processor Array
• Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction
• GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting
• QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initialization
• EYE3:Turn Anything into Naked-eye 3D
• From Gallery to Wrist: Realistic 3D Bracelet Insertion in Videos
• Spherical Epipolar Rectification for Deep Two-View Absolute Depth Estimation
• ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training
• Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance
• Neural Inverse Rendering for High-Accuracy 3D Measurement of Moving Objects with Fewer Phase-Shifting Patterns
• FROSS: Faster-Than-Real-Time Online 3D Semantic Scene Graph Generation from RGB-D Images
• SparseLaneSTP: Leveraging Spatio-Temporal Priors with Sparse Transformers for 3D Lane Detection
• RIOcc: Efficient Cross-Modal Fusion Transformer with Collaborative Feature Refinement for 3D Semantic Occupancy Prediction
• Scene Coordinate Reconstruction Priors
• 2D Gaussian Splatting-based Sparse-view Transparent Object Depth Reconstruction via Physics Simulation for Scene Update
• NeuraLeaf: Neural Parametric Leaf Models with Shape and Deformation Disentanglement
• UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
• Spatially-Varying Autofocus
• EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
• AccidentalGS: 3D Gaussian Splatting from Accidental Camera Motion
• MamV2XCalib: V2X-based Target-less Infrastructure Camera Calibration with State Space Model
• UniOcc: A Unified Benchmark for Occupancy Forecasting and Prediction in Autonomous Driving
• Global-Aware Monocular Semantic Scene Completion with State Space Models
• MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments
• Communication-Efficient Multi-Vehicle Collaborative Semantic Segmentation via Sparse 3D Gaussian Sharing
• VoxelKP: A Voxel-based Network Architecture for Human Keypoint Estimation in LiDAR Data
• Hi-Gaussian: Hierarchical Gaussians under Normalized Spherical Projection for Single-View 3D Reconstruction
• Sat2City: 3D City Generation from A Single Satellite Image with Cascaded Latent Diffusion
• Simulating Dual-Pixel Images From Ray Tracing For Depth Estimation
• Liberated-GS: 3D Gaussian Splatting Independent from SfM Point Clouds
• MS3D: High-Quality 3D Generation via Multi-Scale Representation Modeling
• Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learning
• Explaining Human Preferences via Metrics for Structured 3D Reconstruction
• WIPES: Wavelet-based Visual Primitives
• SP2T: Sparse Proxy Attention for Dual-stream Point Transformer
• RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
• Video2BEV: Transforming Drone Videos to BEVs for Video-based Geo-localization
• EmbodiedSplat: Personalized Real-to-Sim-to-Real Navigation with Gaussian Splats from a Mobile Device
• Benchmarking Burst Super-Resolution for Polarization Images: Noise Dataset and Analysis
• GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding
• CounterPC: Counterfactual Feature Realignment for Unsupervised Domain Adaptation on Point Clouds
• Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes
• Momentum-GS: Momentum Gaussian Self-Distillation for High-Quality Large Scene Reconstruction
• AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes
• MagicCity: Geometry-Aware 3D City Generation from Satellite Imagery with Multi-View Consistency
• S$^3$E: Self-Supervised State Estimation for Radar-Inertial System
• DreamCube: RGB-D Panorama Generation via Multi-plane Synchronization
• Towards Foundational Models for Single-Chip Radar
• BillBoard Splatting (BBSplat): Learnable Textured Primitives for Novel View Synthesis
• NuiScene: Exploring Efficient Generation of Unbounded Outdoor Scenes
• From Gaze to Movement: Predicting Visual Attention for Autonomous Driving Human-Machine Interaction based on Programmatic Imitation Learning
• CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perception
• WonderTurbo: Generating Interactive 3D World in 0.72 Seconds
• Tile-wise vs. Image-wise: Random-Tile Loss and Training Paradigm for Gaussian Splatting
• SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies
• Constraint-Aware Feature Learning for Parametric Point Cloud
• Discontinuity-aware Normal Integration for Generic Central Camera Models
• RoboTron-Sim: Improving Real-World Driving via Simulated Hard-Case
• Inverse 3D Microscopy Rendering for Cell Shape Inference with Active Mesh
• Transformer-based Tooth Alignment Prediction with Occlusion and Collision Constraints
• GVDepth: Zero-Shot Monocular Depth Estimation for Ground Vehicles based on Probabilistic Cue Fusion
• MagShield: Towards Better Robustness in Sparse Inertial Motion Capture Under Magnetic Disturbances
• Stochastic Gradient Estimation for Higher-Order Differentiable Rendering
• ScanEdit: Hierarchically-Guided Functional 3D Scan Editing
• ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation
• NormalLoc: Visual Localization on Textureless 3D Models using Surface Normals
• Towards Safer and Understandable Driver Intention Prediction
• Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cues
• HiP-AD: Hierarchical and Multi-Granularity Planning with Deformable Attention for Autonomous Driving in a Single Decoder
• Splat-based 3D Scene Reconstruction with Extreme Motion-blur
• VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions
• Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View
• Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction
• Lifting the Structural Morphing for Wide-Angle Images Rectification: Unified Content and Boundary Modeling
• MDP-Omni: Parameter-free Multimodal Depth Prior-based Sampling for Omnidirectional Stereo Matching
• VLR-Driver: Large Vision-Language-Reasoning Models for Embodied Autonomous Driving
• Heatmap Regression without Soft-Argmax for Facial Landmark Detection
• SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video
• SViM3D: Stable Video Material Diffusion for Single Image 3D Generation
• You Share Beliefs, I Adapt: Progressive Heterogeneous Collaborative Perception
• CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation
• LoD-Loc v2: Aerial Visual Localization over Low Level-of-Detail City Models using Explicit Silhouette Alignment
• Visual Surface Wave Elastography: Revealing Subsurface Physical Properties via Visible Surface Waves
• Robust Unfolding Network for HDR Imaging with Modulo Cameras
• EVT: Efficient View Transformation for Multi-Modal 3D Object Detection
• Recovering Parametric Scenes from Very Few Time-of-Flight Pixels
• SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansions
• Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrations
• Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
• NeuFrameQ: Neural Frame Fields for Scalable and Generalizable Anisotropic Quadrangulation
• UniGS: Modeling Unitary 3D Gaussians for Novel View Synthesis from Sparse-view Images
• Foresight in Motion: Reinforcing Trajectory Prediction with Reward Heuristics
• Wide2Long: Learning Lens Compression and Perspective Adjustment for Wide-Angle to Telephoto Translation
• Online Language Splatting
• Global Regulation and Excitation via Attention Tuning for Stereo Matching
• SL2A-INR: Single-Layer Learnable Activation for Implicit Neural Representation
• EDM: Efficient Deep Feature Matching
• DONUT: A Decoder-Only Model for Trajectory Prediction
• MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
• GS-ID: Illumination Decomposition on Gaussian Splatting via Adaptive Light Aggregation and Diffusion-Guided Material Priors
• Noise2Score3D: Tweedie's Approach for Unsupervised Point Cloud Denoising
• Driving View Synthesis on Free-form Trajectories with Generative Prior
• RobuSTereo: Robust Zero-Shot Stereo Matching under Adverse Weather
• EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splatting
• AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering
• Debiasing Trace Guidance: Top-down Trace Distillation and Bottom-up Velocity Alignment for Unsupervised Anomaly Detection
• NeurOp-Diff: Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion

Report issues here.