[HN Gopher] VFusion3D: Learning Scalable 3D Generative Models fr...
       ___________________________________________________________________
        
       VFusion3D: Learning Scalable 3D Generative Models from Video
       Diffusion Models
        
       Author : MrTrvp
       Score  : 49 points
       Date   : 2024-08-09 19:55 UTC (1 days ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | MrTrvp wrote:
       | https://arxiv.org/abs/2403.12034
        
       | billconan wrote:
       | I tried a few samples, I feel that its quality is not as good as
       | stable fast 3d.
        
         | vessenes wrote:
         | 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.
        
         | corysama wrote:
         | 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 wrote:
         | And stable fast 3D main point wasn't quality but speed.
        
       ___________________________________________________________________
       (page generated 2024-08-10 23:01 UTC)