All Projects → MandyMo → Pytorch_hmr

MandyMo / Pytorch_hmr

pytorch version of "End-to-end Recovery of Human Shape and Pose"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Pytorch hmr

Expose
ExPose - EXpressive POse and Shape rEgression
Stars: ✭ 254 (-36.82%)
Mutual labels:  human-pose-estimation
React Dynamic Route Loading Es6
Auto chunking and dynamic loading of routes with React Router and Webpack 2
Stars: ✭ 297 (-26.12%)
Mutual labels:  hmr
Pytorch Human Pose Estimation
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
Stars: ✭ 346 (-13.93%)
Mutual labels:  human-pose-estimation
3dmppe rootnet release
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
Stars: ✭ 276 (-31.34%)
Mutual labels:  human-pose-estimation
Semgcn
The Pytorch implementation for "Semantic Graph Convolutional Networks for 3D Human Pose Regression" (CVPR 2019).
Stars: ✭ 290 (-27.86%)
Mutual labels:  human-pose-estimation
Simple Hrnet
Multi-person Human Pose Estimation with HRNet in Pytorch
Stars: ✭ 299 (-25.62%)
Mutual labels:  human-pose-estimation
electron-vue-template
A very simplistic Electron + Vue 3 template including ViteJS and Electron Builder
Stars: ✭ 60 (-85.07%)
Mutual labels:  hmr
Openpose train
Training repository for OpenPose
Stars: ✭ 381 (-5.22%)
Mutual labels:  human-pose-estimation
Posefix release
Official TensorFlow implementation of "PoseFix: Model-agnostic General Human Pose Refinement Network", CVPR 2019
Stars: ✭ 296 (-26.37%)
Mutual labels:  human-pose-estimation
Lightweight Human Pose Estimation 3d Demo.pytorch
Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.
Stars: ✭ 331 (-17.66%)
Mutual labels:  human-pose-estimation
V2v Posenet release
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Stars: ✭ 286 (-28.86%)
Mutual labels:  human-pose-estimation
Tf Simplehumanpose
TensorFlow implementation of "Simple Baselines for Human Pose Estimation and Tracking", ECCV 2018
Stars: ✭ 291 (-27.61%)
Mutual labels:  human-pose-estimation
Webpack Hot Server Middleware
🔥 Hot reload webpack bundles on the server
Stars: ✭ 319 (-20.65%)
Mutual labels:  hmr
Pose Residual Network Pytorch
Code for the Pose Residual Network introduced in 'MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network' paper https://arxiv.org/abs/1807.04067
Stars: ✭ 277 (-31.09%)
Mutual labels:  human-pose-estimation
Posenet Python
A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
Stars: ✭ 350 (-12.94%)
Mutual labels:  human-pose-estimation
aurelia-typescript-webpack-starter
A minimal Aurelia starter kit written in TypeScript and built using webpack.
Stars: ✭ 28 (-93.03%)
Mutual labels:  hmr
Deep High Resolution Net.pytorch
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"
Stars: ✭ 3,521 (+775.87%)
Mutual labels:  human-pose-estimation
Svite
svelte integration for vite
Stars: ✭ 383 (-4.73%)
Mutual labels:  hmr
Darkpose
Distribution-Aware Coordinate Representation for Human Pose Estimation
Stars: ✭ 369 (-8.21%)
Mutual labels:  human-pose-estimation
Electron React Boilerplate
A Foundation for Scalable Cross-Platform Apps
Stars: ✭ 18,727 (+4558.46%)
Mutual labels:  hmr

HMR

This is a pytorch implementation of End-to-end Recovery of Human Shape and Pose by Angjoo Kanazawa, Michael J. Black, David W. Jacobs, and Jitendra Malik, accompanying by some famous human pose estimation networks and datasets. HMR is an end-to end framework for reconstructing a full 3D mesh of a human body from a single RGB image. In contrast to most current methods that compute 2D or 3D joint locations, HMR produce a richer and more useful mesh representation that is parameterized by shape and 3D joint angles. The main objective is to minimize the reprojection loss of keypoints, which allow model to be trained using in-the-wild images that only have ground truth 2D annotations. For visual impact, please visit the author's original video.

training step (the following links are not available now due to license limitation)

1. download the following datasets.

2. download human3.6 datasets.

3. unzip the downloaded datasets.

4. unzip the model.zip

5. config the environment by modify the src/config.py and do_train.sh

6. run ./do_train.sh directly

environment configurations.

  • install pytorch0.4
  • install torchvision
  • install numpy
  • install scipy
  • install h5py
  • install opencv-python

result

reference papers

reference resources

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].