Zan Wang

See [https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/151](https://github.com/yanx27/Pointnet_Pointnet2_pytorch/issues/151)

scene_semantics of 'Werkraum'

3

Loading the 'Werkraum_withlabels.ply' with `trimesh`, I get a `Trimesh` object whose `visual` property is a `TextureVisuals` objects, while other scenes have a `ColorVisuals`. And I can't get the `visual_colors` without...

Why self-conditioning?

2

Are there some works or explanations demonstrating the effectiveness of self-conditioning implementation? Or it is just an empirical trick? https://github.com/lucidrains/denoising-diffusion-pytorch/blob/6e8a0f208265a6e58a3e3d500fdc9f41a6060080/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py#L656-L668

If you use `osmesa` as the backend, please uninstall `pyopengl` and then reinstall it with `pip install pyopengl==3.1.5`.

Hi Chuan, I have been working with the HumanML3D dataset and recently visualized some motion sequences from the HumanAct12 subset. After preprocessing, I noticed that all the motions in this...