StructLDM: Structured Latent Diffusion for 3D Human Generation

Описание к видео StructLDM: Structured Latent Diffusion for 3D Human Generation

Project Page: https://taohuumd.github.io/projects/S...
StructLDM is a diffusion-based unconditional 3D human generative model learned from 2D images. StructLDM enables different levels of controllable 3D human generation and editing, including pose/view/shape control, and high-level tasks including compositional generations, part-aware clothing editing, 3D virtual try-on, etc.

0:00 Generations on RenderPeople
0:31 Generations on UBCFashion
1:07 Compositional Generations
1:32 Novel View Synthesis

Комментарии

Информация по комментариям в разработке

Похожие видео