transmomo.pytorch
transmomo.pytorch copied to clipboard
yzhq97
This is the official PyTorch implementation of the CVPR 2020 paper "TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting".
I want to convert the video like this and save it as Npy: The file should contain an array with shape 15 x 2 x length. The first dimension (15)...
Hi! I've noticed in the paper that the 2D pose can be generated by projecting 3D into 2D, and the retargeting inference that the repo provides is 2D pose generation....
how to generate a numpy .npy file from DensePose?
Thanks for you sharing codes.Could you provide an example for generating a numpy `.npy` file with `Detectron2`?Thanks again.
I want to know what is unit meaning in this function. Hope for your reply. `def preprocess_test(motion, meanpose, stdpose, unit=128): motion = motion * unit motion[1, :, :] = (motion[2,...
Hi @yzhq97, I am facing issue regarding the limb normalisation. I have been trying to normalise each to the limb lengths in scale between 0-1. But it seems that it...
Hi，I use detectron2 get the 15 keypoints，but the x and y coordinates in data/solo_dance are decimals,so what can I do to convert integers to decimals.
Hello author, I want to generate a video with a 256*256 skeleton keypoint .npy file. In the output video, the key points are deviated greatly. https://github.com/yzhq97/transmomo.pytorch/assets/108513330/f223ebe5-3422-4d2f-bfda-50ff273fa316
Hi, if I have a single human image, and I want to make the image animate by the driving video. Does this repository works? Thank you in advance!
