MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

Arxiv 2024


Shitao Tang1*, Jiacheng Chen1*, Dilin Wang2*, Chengzhou Tang2, Fuyang Zhang1, Yuchen Fan2, Vikas Chandra2, Yasutaka Furukawa†1, Rakesh Ranjan†2

1Simon Fraser University    2Meta Reality Labs    

1*Equal contribution. † Joint last author. Contact the authors at shitaot@sfu.ca.   


Sparse view Reconsteruction results (31-40/48)

MVDiffusion++ is able to generate dense, high-resolution images conditioned on a single or multiple unposed images
Left: generated images, Right: textured mesh
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF
1-view generation 2-view generation 4-view generation
Description of GIF Description of GIF Description of GIF
1st view 2nd view 3rd view 4th view
Description of GIF