chunyuwang Goto Github PK

academic-kickstart-1

Easily create a beautiful website using Academic and Hugo

albumentations

fast image augmentation library and easy to use wrapper around other libraries

caffe-model

Caffe models (imagenet pretrain) and prototxt generator scripts for inception_v3 \ inception_v4 \ inception_resnet \ fractalnet \ resnext

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

dotfiles

Collection of dotfiles

easymocap-1

Make human motion capture easier.

evaluation

fairmot

A simple baseline for one-shot multi-object tracking

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.

gcr-notebook

h36m-toolbox

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!

human-pose-estimation.pytorch

The project is an official implement of our ECCV2018 paper "Simple Baselines for Human Pose Estimation and Tracking(https://arxiv.org/abs/1804.06208)"

ik

Minimal Inverse Kinematics library

ikpy

An Inverse Kinematics library aiming performance and modularity

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".

lcn-pose

This is an official implementation of the work "Optimizing Network Structure for 3D Human Pose Estimation, ICCV 2019"

manifold

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.

pacom

pct

This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)

pytorch-best-practice

PyTorch实践指南对应代码

pytorch3d

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data