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

Re:VFusion3D: Learning Scalable 3D Generative Models from Vi... by billconan on Friday August 09, 2024 @06:37PM (#41205940)

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

[ Parent | on HN ]

Re:VFusion3D: Learning Scalable 3D Generative Models from Vi... by corysama on Friday August 09, 2024 @08:10PM (#41206432)

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.

[ Parent | on HN ]

Re:VFusion3D: Learning Scalable 3D Generative Models from Vi... by vessenes on Friday August 09, 2024 @07:56PM (#41206382)

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.

[ Parent | on HN ]

Re:VFusion3D: Learning Scalable 3D Generative Models from Vi... by iTokio on Saturday August 10, 2024 @08:41AM (#41209048)

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

[ Parent | on HN ]