Poster
GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation
Phillip Mueller · Talip Ünlü · Sebastian Schmidt · Marcel Kollovieh · Jiajie Fan · Stephan Günnemann · Lars Mikelsons
Precise geometric control in image generation is essential for fields like engineering \& product design and creative industries to control 3D object features accurately in 2D image space. Traditional 3D editing approaches are time-consuming and demand specialized skills, while current image-based generative methods lack accuracy in geometric conditioning. To address these challenges, we propose GeoDiffusion, a training-free framework for accurate and efficient geometric conditioning of 3D features in image generation. GeoDiffusion employs a class-specific 3D object as a geometric prior to define keypoints and parametric correlations in 3D space. We ensure viewpoint consistency through a rendered image of a reference 3D object, followed by style transfer to meet user-defined appearance specifications. At the core of our framework is GeoDrag, improving accuracy and speed of drag-based image editing on geometry guidance tasks and general instructions on DragBench. Our results demonstrate that GeoDiffusion enables precise geometric modifications across various iterative design workflows.
Live content is unavailable. Log in and register to view live content