Mosaic-SDF for 3D Generative Models

arXiv:2312.09222v2 Announce Type: replace
Abstract: Current diffusion or flow-based generative models for 3D shapes divide to two: distilling pre-trained 2D image diffusion models, and training directly on 3D shapes. When training a diffusion or flow models on 3D shapes a crucial design choice is the shape representation. An effective shape representation needs to adhere three design principles: it should allow an efficient conversion of large 3D datasets to the representation form; it should provide a good tradeoff of approximation power …

2d image abstract arxiv cs.cv cs.gr current design diffusion diffusion models flow generative generative models image image diffusion mosaic representation training type