Edit ZJU-MoCap (ZJU-MoCap Dataset) LightStage is a multi-view dataset, which is proposed in NeuralBody. This dataset captures multiple dynamic human videos using a multi-camera system that has 20+ synchronized cameras. The humans perform complex motions, including twirling, Taichi, arm swings,...
If you would like to download the ZJU-Mocap dataset, please sign the agreement, and email it to Qing Shuai (s_q@zju.edu.cn) and cc Xiaowei Zhou (xwzhou@zju.edu.cn) to request the download link. LightStage: captured with LightStage system Mirrored-Human: collected from the Internet ...
SEQUENCES=("my_377" "my_386" "my_387" "my_392" "my_393" "my_394") for SEQUENCE in ${SEQUENCES[@]}; do dataset="data/zju_mocap_refine/$SEQUENCE" python train.py -s $dataset --eval --exp_name zju_mocap_refine/${SEQUENCE}_100_pose_correction_lbs_offset_split_clone_merge_prun...