MVDream: Multi-view Diffusion for 3D Generation

Paper Project Code Gallery

All Testing Results (11-20 / 40)

We use the threestudio implementation for all the baselines. A fixed configuration is used for each method (including ours) without prompt-wise hyperparameter tuning. The results here are without cherry picking.

Dreamfusion-IF

Magic3D-IF-SD

Text2Mesh-IF

ProlificDreamer

Ours

Flying Dragon, highly detailed, breathing fire

A bald eagle carved out of wood

Pedestal Fan (White)

a DSLR photo of a frog wearing a sweater

a DSLR photo of a ghost eating a hamburger

mecha vampire girl chibi

A 3D scan of AK47, weapon

Darth Vader helmet,g highly detailed

A photo of a horse walking

Fisherman House, cute, cartoon, blender, stylized


Citation

@article{shi2023MVDream,
  author = {Shi, Yichun and Wang, Peng and Ye, Jianglong and Mai, Long and Li, Kejie and Yang, Xiao},
  title = {MVDream: Multi-view Diffusion for 3D Generation},
  journal = {arXiv:2308.16512},
  year = {2023},
}