EXIT
EXIT
the input has 4 dimensions ```[batch size, # of frames, # of joints, dim]``` ``` batch size = 64 # of frames = 60 # of joints = 17 dim...
Yeah, the other skeleton-based methods should be similar. GaitGraph has even less computation because it's using graph convolution in the spatial dimension while GaitMixer is using self-attention. But to be...
It's high variance due to the small data regime and noise from pose estimation. Especially, the "Coat" condition has the highest variance. So we run 8 experiments for each architecture...
Yes. We use the same default parameters as common.py. For BG and CL, the evaluation has very high variance but NM should not see much difference. Can you run an...
1. I follow "Render SMPL mesh" in [MDM](https://github.com/GuyTevet/motion-diffusion-model) to render .obj and use blender to render images. 2. Or you can follow "SMPL Mesh Rendering" in [T2M-GPT](https://github.com/Mael-zys/T2M-GPT) to render images...
Thank you for clarification.
Hi, and thank you again for open-sourcing your amazing work. I have a hard time replicate the evaluation on Table 1. 1. Can you provide the command to run the...
Thank you for your interest in our work. I did not clean the code for training yet. But I already put the raw code in the repo. Here is the...
Hi thank you for creating an issue. I updated the link. It should work now. ``` bash dataset/prepare/download_extractor.sh ```
Hi, thank you for your interest. It should be fine. It uses around ~17 GB, 1GPU, with batchsize 128 (in 2nd stage) for training.