Kitsunetic

Thank you such a great work. I have question about `p2_loss_weight` in [here](https://github.com/lucidrains/denoising-diffusion-pytorch/blob/9939a481390d9223d607b7a09fd01a292494702f/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py#L432). ```py # calculate p2 reweighting register_buffer("p2_loss_weight", (p2_loss_weight_k + alphas_cumprod / (1 - alphas_cumprod)) ** -p2_loss_weight_gamma) ``` It...

Thank you for great work I'm curious about what `train_overfit.lst` and `test_overfit.lst` mean in the preprocessed dataset which can be downloaded in [*Dataset for Learning-based Reconstruction*](https://github.com/autonomousvision/shape_as_points#dataset-for-learning-based-reconstruction)? I cannot find any...

How many points sampled from the complete mesh?

1

Thank you for a great work I want to know how many points are sampled from the completed meshes when calculating CD, F1, FPD in table 1 and table 3...

I found some bugs and fixed it. Please check my pull request. 1. Parameter `loss_type` is being ignored in both `ContextualLoss` and `ContextualBilateralLoss`. 2. Parameter `band_width` in `ContextualBilateralLoss` is treated...

I found some bugs and fixed it. Please check my pull request. 1. Parameter `loss_type` is being ignored in both `ContextualLoss` and `ContextualBilateralLoss`. 2. Parameter `band_width` in `ContextualBilateralLoss` is treated...

How about ChamferDistance instead of cdist to calculate KNN?

2

Hi, I propose to use KNN function that is used in point cloud field instead of `torch.cdist`. VectorQuantization finds nearest vector inside of the codebook (B, M, D) with given...

Reconstruction loss in supp

2

Hi, Thank you for great work. I have question about the Eq.1 of supp. $\mathcal L_\text{VQ-VAE}=-\log p(X|\mathbf Z) + \|\| \text{sg}[\hat{\mathbf Z}]-\mathbf Z\|\|^2_2+\|\| \hat{\mathbf Z} - \text{sg}[\mathbf Z]\|\|^2_2$ But in...

Change not only title bar but status bar color too. ### For example 

The preprocessing script `preprocessing_amass.py` does not generate any preprocessed data for certain AMASS subsets (CNRS, EKUT, KIT). For all data in these subsets, it consistently shows error messages like `frame...

I'm currently working on applying your pretrained model to another environment, and I have come across a couple of questions related to your evaluation code while working with the CHI3D...