Official code release for 3DV 2021 paper Human Performance Capture from Monocular Video in the Wild.

Last update: Dec 24, 2022

Overview

Human Performance Capture from Monocular Video in the Wild

Paper | Video | Project Page

Official code release for 3DV 2021 paper Human Performance Capture from Monocular Video in the Wild. We propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses, without any additional input.

If you find our code or paper useful, please cite as

@inproceedings{guo2021human,
  title={Human Performance Capture from Monocular Video in the Wild},
  author={Guo, Chen and Chen, Xu and Song, Jie and Hilliges, Otmar},
  booktitle={2021 International Conference on 3D Vision (3DV)},
  pages={889--898},
  year={2021},
  organization={IEEE}
}

Quick Start

CLone this repo:

git clone https://github.com/MoyGcc/hpcwild.git
cd  hpcwild
conda env create -f environment.yml
conda activate hpcwild

Additional Dependencies:

Kaolin 0.1.0 (https://github.com/NVIDIAGameWorks/kaolin)
MPI mesh library (https://github.com/MPI-IS/mesh)
torch-mesh-isect (https://github.com/vchoutas/torch-mesh-isect)

Download SMPL models (1.0.0 for Python 2.7 (10 shape PCs)) and move them to the corresponding places:

mkdir lib/smpl/smpl_model/
mv /path/to/smpl/models/basicModel_f_lbs_10_207_0_v1.0.0.pkl smpl_rendering/smpl_model/SMPL_FEMALE.pkl
mv /path/to/smpl/models/basicmodel_m_lbs_10_207_0_v1.0.0.pkl smpl_rendering/smpl_model/SMPL_MALE.pkl

Download checkpoints for external modules:

wget https://download.01.org/opencv/openvino_training_extensions/models/human_pose_estimation/checkpoint_iter_370000.pth
mv /path/to/checkpoint_iter_370000.pth external/lightweight-human-pose-estimation.pytorch/checkpoint_iter_370000.pth

wget https://dl.fbaipublicfiles.com/pifuhd/checkpoints/pifuhd.pt pifuhd.pt 
mv /path/to/pifuhd.pt external/pifuhd/checkpoints/pifuhd.pt

Download IPNet weights: https://datasets.d2.mpi-inf.mpg.de/IPNet2020/IPNet_p5000_01_exp_id01.zip
unzip IPNet_p5000_01_exp_id01.zip
mv /path/to/IPNet_p5000_01_exp_id01 registration/experiments/IPNet_p5000_01_exp_id01

gdown --id 1mcr7ALciuAsHCpLnrtG_eop5-EYhbCmz -O modnet_photographic_portrait_matting.ckpt
mv /path/to/modnet_photographic_portrait_matting.ckpt external/MODNet/pretrained/modnet_photographic_portrait_matting.ckpt

Test on 3DPW dataset

Download 3DPW dataset

modify the dataset_path in test.conf.
run bash mesh_recon.sh to obtain the rigid body shape.
run bash registration.sh to register a SMPL+D model to the rigid human body.
run bash tracking.sh to capture the human performance temporally.

Test on your own video

run OpenPose to obtain the 2D keypoints.
run LGD to acquire the initial 3D poses.
run MODNet to extract sihouettes.

Acknowledgement

We use the code in PIFuHD for the rigid body construction and adapt IPNet for human model registration. We use off-the-shelf methods OpenPose and MODNet for the extraction of 2D keypoints and sihouettes. We sincerely thank these authors for their awesome work.

Official code release for 3DV 2021 paper Human Performance Capture from Monocular Video in the Wild.

Related tags

Overview

Human Performance Capture from Monocular Video in the Wild

Paper | Video | Project Page

Quick Start

Test on 3DPW dataset

Test on your own video

Acknowledgement

Owner

Chen Guo

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

Machine learning evaluation metrics, implemented in Python, R, Haskell, and MATLAB / Octave

Pytorch based library to rank predicted bounding boxes using text/image user's prompts.

Pairwise Learning for Neural Link Prediction for OGB (PLNLP-OGB)

Production First and Production Ready End-to-End Speech Recognition Toolkit

Dynamical movement primitives (DMPs), probabilistic movement primitives (ProMPs), spatially coupled bimanual DMPs.

Implement some metaheuristics and cost functions

(JMLR'19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

Pytorch implementation for the EMNLP 2020 (Findings) paper: Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering

Fake News Detection Using Machine Learning Methods

Segmentation-Aware Convolutional Networks Using Local Attention Masks

A minimalist environment for decision-making in autonomous driving

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

This is the open-source reference implementation of the SIGGRAPH 2021 paper Intersection-free Rigid Body Dynamics.

An open source python library for automated feature engineering

Companion code for the paper Theoretical characterization of uncertainty in high-dimensional linear classification

DLL: Direct Lidar Localization

Object-aware Contrastive Learning for Debiased Scene Representation

An end-to-end framework for mixed-integer optimization with data-driven learned constraints.

SIMULEVAL A General Evaluation Toolkit for Simultaneous Translation