Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
| Date | Stars |
|---|---|
| 2026-07-24 | 491 |
| 2026-07-25 | 491 |
| 2026-07-28 | 491 |
| 2026-07-30 | 491 |
| 2026-08-06 | 491 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# RootNet of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image"
<p align="center">
<img src="assets/qualitative_intro.PNG" width="800" height="300">
</p>
<p align="middle">
<img src="assets/posetrack_1.gif" width="200" height="150"> <img src="assets/posetrack_2.gif" width="200" height="150"><img src="assets/posetrack_3.gif" width="200" height="150"> <img src="assets/posetrack_4.gif" width="200" height="150">
</p>
## Introduction
This repo is official **[PyTorch](https://pytorch.org)** implementation of **[Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image (ICCV 2019)](https://arxiv.org/abs/1907.11346)**. It contains **RootNet** part.
**What this repo provides:**
* [PyTorch](https://pytorch.org) implementation of [Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image (ICCV 2019)](https://arxiv.org/abs/1907.11346).
* Flexible and simple code.
* Compatibility for most of the publicly available 2D and 3D, single and multi-person pose estimation datasets including **[Human3.6M](http://vision.imar.ro/human3.6m/description.php), [MPII](http://human-pose.mpi-inf.mpg.de/), [MS COCO 2017](http://cocodataset.org/#home), [MuCo-3DHP](http://gvv.mpi-inf.mpg.de/projects/SingleShotMultiPerson/), [MuPoTS-3D](http://gvv.mpi-inf.mpg.de/projects/SingleShotMultiPerson/), and [3DPW](https://virtualhumans.mpi-inf.mpg.de/3DPW/)**.
* Human pose estimation visualization code.
## Dependencies
* [PyTorch](https://pytorch.org)
* [CUDA](https://developer.nvidia.com/cuda-downloads)
* [cuDNN](https://developer.nvidia.com/cudnn)
* [Anaconda](https://www.anaconda.com/download/)
* [COCO API](https://github.com/cocodataset/cocoapi)
This code is tested under Ubuntu 16.04, CUDA 9.0, cuDNN 7.1 environment with two NVIDIA 1080Ti GPUs.
Python 3.6.5 version with Anaconda 3 is used for development.
## Quick demo
You can try quick demo at `demo` folder.
* Download the pre-trained RootNet in [here](https://drive.google.com/file/d/1ZHoXNFxBBsmis-5Xzu7dfXYGNxjpntgt/view?usp=sharing).
* Prepare `input.jpg` and pre-trained snapshot at `demo` folder.
* Set `bbox_list` at [here](https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE/blob/ca25760a2d60272a5952cd6612a69b65dc926be3/demo/demo.py#L62).
* Run `python demo.py --gpu 0 --test_epoch 18` if you want to run on gpu 0.
* You can see `output_root_2d.jpg` and printed root joint depths.
## Directory
### Root
The `${POSE_ROOT}` is described as below.
```
${POSE_ROOT}
|-- data
|-- demo
|-- common
|-- main
|-- output
```
* `data` contains data loading codes and soft links to images and annotations directories.
* `demo` contains demo codes.
* `common` contains kernel codes for 3d multi-person pose estimation system.
* `main` contains high-level codes for training or testing the network.
* `output` contains log, trained models, visualized outputs, and test result.
### Data
You need to follow directory structure of the `data` as below.
```
${POSE_ROOT}
|-- data
| |-- Human36M
| | |-- bbox
| | | |-- bbox_human36m_output.json
| | |-- images
| | |-- annotations
| |-- MPII
| | |-- images
| | |-- annotations
| |-- MSCOCO
| | |-- images
| | | |-- train2017
| | | |-- val2017
| | |-- annotations
| |-- MuCo
| | |-- data
| | | |-- augmented_set
| | | |-- unaugmented_set
| | | |-- MuCo-3DHP.json
| |-- MuPoTS
| | |-- bbox
| | | |-- bbox_mupots_output.json
| | |-- data
| | | |-- MultiPersonTestSet
| | | |-- MuPoTS-3D.json
| |-- PW3D
| | |-- data
| | | |-- 3DPW_train.json
| | | |-- 3DPW_validation.json
| | | |-- 3DPW_test.json
| | |-- imageFiles
```
* Download Human3.6M parsed data [[data](https://drive.google.com/drive/folders/1r0B9I3XxIIW_jsXjYinDpL6NFcxTZart?usp=sharing)]
* Download MPII parsed data [[images](http://human-pose.mpi-inf.mpg.de/)][[annotations](httpsExcerpt of 9,250 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:996ae66ce4c2226b, topic:deep-learning, topic:pytorch
matched fp:996ae66ce4c2226b, topic:computer-vision, desc:pose estimation, readme:pose estimation