Settings

Theme

VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models

github.com

56 points by MrTrvp a year ago · 5 comments

Reader

billconan a year ago

I tried a few samples, I feel that its quality is not as good as stable fast 3d.

  • corysama a year ago

    I'm guessing this paper is more about "It's neat that this works at all." rather than trying to improve on the state of the art.

  • iTokio a year ago

    And stable fast 3D main point wasn’t quality but speed.

  • vessenes a year ago

    Interesting that they compare to totally different models than Stable Fast 3D’s paper. I’m not clear on relative size of VFusion3D vs Stable Fast 3D, but I do think the training idea is good and novel — getting relatively good quality out of movies is a much easier ask in terms of collecting training data than getting 3D model renderings.

MrTrvpOP a year ago

https://arxiv.org/abs/2403.12034

Keyboard Shortcuts

j
Next item
k
Previous item
o / Enter
Open selected item
?
Show this help
Esc
Close modal / clear selection