JHnvidia

Hi @9of9, I'm just speculating, but 19 views sounds like it's probably on the low side. Additionally you can expect mesh quality to degrade if camera poses and segmentation masks...

Hello, We used the https://github.com/otaheri/chamfer_distance package for chamfer distance, and [trimesh](https://trimsh.org/) to load meshes & sample point clouds. We used 2.5M points for the results in the paper, but you...

Hi, As mentioned in the error message the **tinycudann** package failed to install due to compilation errors. There's a few version conflicts between MSVC/CUDA versions that sometimes causes these errors,...

Hi, This error is related to nvdiffrast (which is a dependency), so i would recommend first installing and trying to run an example from nvdiffrast to see if that works....

Hi @sirisian, I don't think we'll do significant memory optimizations to the code in the short term. We want it to stay true to the paper version, and as researchers...

Please note that we do not expect good quality results from CO3D as it breaks many of our assumptions. Compared to the nerf/nerd datasets it has less controlled lighting, lower...

Hi, Unfortunately I cannot recreate this error locally. The error means that the training/optimization diverges, once optimization removes all geometry from the scene you get stuck in a non-recoverable state...

Hi, We've tried a bit more to recreate the error, but are unable. The error is quite strange, as the `kd_grad` regularizer just directly takes the texture albedo. My best...

Hi @pean1128, This is intentional. For our trained geometry, we're always using smooth normals (because supporting creases etc would be more difficult). We assume that if there's a sharp normal...

@iraj465, From the error message it also looks like your images are missing the alpha component. We assume that the dataset loader generates a 4-component output image (r,g,b,a) where alpha...