Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion

arXiv:2311.15980v2 Announce Type: replace
Abstract: Recent advances in generative AI have unveiled significant potential for the creation of 3D content. However, current methods either apply a pre-trained 2D diffusion model with the time-consuming score distillation sampling (SDS), or a direct 3D diffusion model trained on limited 3D data losing generation diversity. In this work, we approach the problem by employing a multi-view 2.5D diffusion fine-tuned from a pre-trained 2D diffusion model. The multi-view 2.5D diffusion directly models the structural distribution …

arxiv cs.cv diffusion diverse text type via view