Qualtitative result	Paper teaser video

• Update 22.06.17: Now you can reproduce Table 6! No change on running commands.
• Update 22.06.06: NeuralAnnot SMPL annotations of Human36M are released!

This repository is the official Pytorch implementation of Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video. Find more qualitative results here. The base codes are largely borrowed from VIBE.

TCMR is tested on Ubuntu 16.04 with Pytorch 1.4 and Python 3.7.10. You may need sudo privilege for the installation.

source scripts/install_pip.sh

If you have a problem related to torchgeometry, please check this out.

• Download the pre-trained demo TCMR and required data by below command and download SMPL layers from here (male&female) and here (neutral). Put SMPL layers (pkl files) under ${ROOT}/data/base_data/.

source scripts/get_base_data.sh

• Run demo with options (e.g. render on plain background). See more option details in bottom lines of demo.py.
• A video overlayed with rendered meshes will be saved in ${ROOT}/output/demo_output/.

python demo.py --vid_file demo.mp4 --gpu 0 

Here I report the performance of TCMR.

See our paper for more details.

Download pre-processed data (except InstaVariety dataset) from here. Pre-processed InstaVariety is uploaded by VIBE authors here. You may also download datasets from sources and pre-process yourself. Refer to this. Put SMPL layers (pkl files) under ${ROOT}/data/base_data/.

The data directory structure should follow the below hierarchy.

${ROOT}  
|-- data  
|   |-- base_data  
|   |-- preprocessed_data  
|   |-- pretrained_models

• Download pre-trained TCMR weights from here.
• Run the evaluation code with a corresponding config file to reproduce the performance in the tables of our paper.

# dataset: 3dpw, mpii3d, h36m 
python evaluate.py --dataset 3dpw --cfg ./configs/repr_table4_3dpw_model.yaml --gpu 0 

• You may test options such as average filtering and rendering. See the bottom lines of ${ROOT}/lib/core/config.py.
• We checked rendering results of TCMR on 3DPW validation and test sets.

• Run the training code with a corresponding config file to reproduce the performance in the tables of our paper.
• There is a hard coding related to the config file's name. Please use the exact config file to reproduce, instead of changing the content of the default config file.

# training outputs are saved in `experiments` directory
# mkdir experiments
python train.py --cfg ./configs/repr_table4_3dpw_model.yaml --gpu 0 

• After the training, the checkpoints are saved in ${ROOT}/experiments/{date_of_training}/. Change the config file's TRAIN.PRETRAINED with the checkpoint path (either checkpoint.pth.tar or model_best.pth.tar) and follow the evaluation command.
• You may test the motion discriminator introduced in VIBE by uncommenting the codes that have exclude motion discriminator notations.

@InProceedings{choi2020beyond,
  title={Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video},
  author={Choi, Hongsuk and Moon, Gyeongsik and Chang, Ju Yong and Lee, Kyoung Mu},
  booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)}
  year={2021}
}

This project is licensed under the terms of the MIT license.

I2L-MeshNet_RELEASE
3DCrowdNet_RELEASE
TCMR_RELEASE
Hand4Whole_RELEASE
HandOccNet
NeuralAnnot_RELEASE