KU-CVLAB / 3DFuse

Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"
711 stars 42 forks source link

Why green background #17

Closed Adamdad closed 1 year ago

Adamdad commented 1 year ago

Firstly, I would like to express my gratitude for your excellent work.

However, I have noticed that when I run the code, the resulting nerf model consistently appears with a green background color, and I am unsure about the reason behind this. I would like to inquire if you have any insights or suggestions regarding this issue.

It's worth mentioning that I haven't observed this phenomenon with other methods such as SJC and Dreambooth. I would appreciate any help you can provide in resolving this matter.

Thank you.

j0seo commented 1 year ago

Thanks for your interest in our work! Our work is based on voxel-based radiance fields in a latent space, the same as SJC. In our setting, blend_bg_texture is set to False by default. If you change it to True, you can see a textured background shown in SJC. As our work is designed for generating objects, the background is not reconstructed together, and we set the default color to green. To change this, you can check this part (although it is not easy to adjust for desired color accurately as it is rendered in the latent space). If you have any more questions, please feel free to ask!