Cheng Lin

Hi, you can amend this function, to output different meshes based on the face labels https://github.com/clinplayer/SEG-MAT/blob/400ee4d6901987606c542219ff93a2d3cc44c049/src/Decomposer.cpp#L35 You can also try to use the colors of the output mesh to categorize...

Hey, I can't reimplement this issue. I think this error is caused by using an index that is outside the range of dimensions of a CUDA tensor in CUDA tensor...

Hey, I cannot reproduce this problem. This is a problem for the pointnet++ installation, so could you please check if the issues or the guidelines in https://github.com/erikwijmans/Pointnet2_PyTorch can help? We...

Hi, this is a problem with PointNet installation. Could you please check if the instructions on https://github.com/erikwijmans/Pointnet2_PyTorch can help?

Hey, could you show me your training curve for the reward? How about the reward of IL? Let us first confirm whether the IL stage learns good policies.

I remember I encountered an issue with the IL process, and the RL process does not start with a good policy. I'm not sure if this also leads to your...

> Hello, I am recently training both Prim and Mesh agents on airplane and guitar datasets using the depth image input as well. But I am also not sure whether...

I'm afraid not. But you can download the source code provided by the author and convert it to command line interface https://binwangthss.github.io/qmat/qmat.html

Yes! If you know the camera poses, a potential way is to unproject the multiview image features to the 3D feature volume, and then you can condition the denoising process...

Hi, all the implementations are based on the opencv coordinate system.