GeoDiffuser: Geometry-Based Image Editing with Diffusion Models

arXiv:2404.14403v1 Announce Type: new
Abstract: The success of image generative models has enabled us to build methods that can edit images based on text or other user input. However, these methods are bespoke, imprecise, require additional information, or are limited to only 2D image edits. We present GeoDiffuser, a zero-shot optimization-based method that unifies common 2D and 3D image-based object editing capabilities into a single method. Our key insight is to view image editing operations as geometric transformations. We show …

arxiv cs.cv diffusion diffusion models editing geometry image type