Chunyu Wang's repositories
imu-human-pose-pytorch
This is an official Pytorch implementation of "Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach, CVPR 2020".
EasyMocap-1
Make human motion capture easier.
TotalCapture-Toolbox
A toolbox for processing Total Capture dataset
voxelpose-pytorch
Official implementation of "VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment"
albumentations
fast image augmentation library and easy to use wrapper around other libraries
camera_calibration
Code and resources for camera calibration using arUco markers and opencv
cvpr2018nkn
Tensorflow implementation of the CVPR 2018 paper: Neural Kinematic Networks for Unsupervised Motion Retargetting
flame-fitting
Example code for the FLAME 3D head model. The code demonstrates how to sample 3D heads from the model, fit the model to 3D keypoints and 3D scans.
HigherHRNet-Human-Pose-Estimation
This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)
hugo-academic
📝 The website builder for Hugo. Build and deploy a beautiful website in minutes!
Minimal-IK
Solving SMPL/MANO parameters from keypoint coordinates.
MMPose_Tutorials
Jupyter notebook tutorials for mmpose
MocapNET
We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).
moveit_whole_body_ik
Non-chain inverse kinematics solver for MoveIt!
multiview-human-pose-estimation-pytorch-1
This is an official Pytorch implementation of "Cross View Fusion for 3D Human Pose Estimation, ICCV 2019". It establishes a new state-of-the-art in this field. The 3D error of our approach is about 26mm on the H36M dataset.
nerf-pytorch
A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.
PCT
This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)
VideoTo3dPoseAndBvh
Convert video to the bvh motion file
VolumeDiffusion
Flexible Text-to-3D Generation with Efficient Volumetric Encoder