cjy
cjy
I am very grateful for your quick and detailed response. However, I still have some questions: 1. In question 2, I still have some confusion. According to your paper, when...
Training on NeRF representation only returns white images for the rendered images and no depth maps.
I've encountered the same issue. I checked your processing in the dataset [https://github.com/TencentARC/InstantMesh/blob/main/src/data/objaverse.py#L186](https://github.com/TencentARC/InstantMesh/blob/main/src/data/objaverse.py#L186) and you've already converted the world-to-camera matrix to the camera-to-world matrix, so it shouldn't be that. I...
same issue. I want to use TextClip, but both 2.1.1 and 1.0.3 can't handle this, so I switched to 2.1.2. It works, but it's very, very slow.