Open yejr0229 opened 1 week ago
yeah, we have discussed the multi-face problem in our paper. This issue primarily arises from the inconsistency of multi-view texture images sampled from the pre-trained 2D diffusion model, as it is not explicitly trained on multi-view datasets.
Some new models (zero123, EscherNet) consider camera pose during the diffusion process, which may alleviate the multi-face problem.
Hi, I use txet to texture to paint my 3D model and get:
and here is the front and back view of my mesh:
So I wonder the mutil-view consistence of Piant3D may not be good, I think it's due to the original depth diffusion can not aware the viewpoint, please let me know your thoughts, thanks a lot