Tiange Xiang

Hi, Thanks for your efforts on this! Glad to see CurveNet performs the best on your benchmark. I will make an update in the README to highlight such result and...

Hi, the voting script we used was **identical** to the ones used in RSCNN, therefore we didn't keep particular records of the script itself. It is really weird that the...

This is because, in FPS, we only want to start from the first index node (0th node) for eliminating any randomness. If this causes the problem in voting, maybe you...

Hi, thanks for your interest! As mentioned in README.md, we used the exact voting scripts provided in [RSCNN](https://github.com/Yochengliu/Relation-Shape-CNN). Simply update the scripts with our dataloader/model and you are good to...

Hi, visualization of curves is essentially the drawing of connections between the selected nodes in order. In this case, you can simply collect the ```flatten_cur``` parameters [here](https://github.com/tiangexiang/CurveNet/blob/main/core/models/walk.py#L138) at every step,...

Hi, this error means the ShapeNet dataset has not been loaded (and therefore the array is empty). This error is probably related to https://github.com/tiangexiang/CurveNet/issues/4#issuecomment-897089842. Can you please make sure the...

Thanks for your interest! A license file regarding this repository has been uploaded. Thanks!

Hi, 0.927 classification accuracy is really strange, the plain backbone (even DGCNN) performs much better than this. Can you please post your training log? That will help identify the problem....

I have re-evaluated the repo on two different machines, both got consistent results (0.9371 and 0.9363). Can you please doublecheck there are not any changes to the original code? If...

Thanks for your response! Just double check, in your ICCV paper: 1) The only datasets that have SMPL param gts you used are **h36m** and **MPII**? 2) Did your use...