Home

Awesome

PoseNet 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 implementation of Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image (ICCV 2019). It contains PoseNet part.

What this repo provides:

Dependencies

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.

Directory

Root

The ${POSE_ROOT} is described as below.

${POSE_ROOT}
|-- data
|-- demo
|-- common
|-- main
|-- tool
|-- vis
`-- output

Data

You need to follow directory structure of the data as below.

${POSE_ROOT}
|-- data
|   |-- Human36M
|   |   |-- bbox_root
|   |   |   |-- bbox_root_human36m_output.json
|   |   |-- images
|   |   |-- annotations
|   |-- MPII
|   |   |-- images
|   |   |-- annotations
|   |-- MSCOCO
|   |   |-- bbox_root
|   |   |   |-- bbox_root_coco_output.json
|   |   |-- images
|   |   |   |-- train2017
|   |   |   |-- val2017
|   |   |-- annotations
|   |-- MuCo
|   |   |-- data
|   |   |   |-- augmented_set
|   |   |   |-- unaugmented_set
|   |   |   |-- MuCo-3DHP.json
|   |-- MuPoTS
|   |   |-- bbox_root
|   |   |   |-- bbox_mupots_output.json
|   |   |-- data
|   |   |   |-- MultiPersonTestSet
|   |   |   |-- MuPoTS-3D.json

To download multiple files from Google drive without compressing them, try this. If you have a problem with 'Download limit' problem when tried to download dataset from google drive link, please try this trick.

* Go the shared folder, which contains files you want to copy to your drive  
* Select all the files you want to copy  
* In the upper right corner click on three vertical dots and select “make a copy”  
* Then, the file is copied to your personal google drive account. You can download it from your personal account.  

Output

You need to follow the directory structure of the output folder as below.

${POSE_ROOT}
|-- output
|-- |-- log
|-- |-- model_dump
|-- |-- result
`-- |-- vis

3D visualization

Running 3DMPPE_POSENET

Start

Train

In the main folder, run

python train.py --gpu 0-1

to train the network on the GPU 0,1.

If you want to continue experiment, run

python train.py --gpu 0-1 --continue

--gpu 0,1 can be used instead of --gpu 0-1.

Test

Place trained model at the output/model_dump/.

In the main folder, run

python test.py --gpu 0-1 --test_epoch 20

to test the network on the GPU 0,1 with 20th epoch trained model. --gpu 0,1 can be used instead of --gpu 0-1.

Results

Here I report the performance of the PoseNet.

Human3.6M dataset using protocol 1

For the evaluation, you can run test.py or there are evaluation codes in Human36M.

<p align="center"> <img src="assets/H36M_P1.png"> </p>

Human3.6M dataset using protocol 2

For the evaluation, you can run test.py or there are evaluation codes in Human36M.

<p align="center"> <img src="assets/H36M_P2.png"> </p>

MuPoTS-3D dataset

For the evaluation, run test.py. After that, move data/MuPoTS/mpii_mupots_multiperson_eval.m in data/MuPoTS/data. Also, move the test result files (preds_2d_kpt_mupots.mat and preds_3d_kpt_mupots.mat) in data/MuPoTS/data. Then run mpii_mupots_multiperson_eval.m with your evaluation mode arguments.

<p align="center"> <img src="assets/MuPoTS.png"> </p>

MSCOCO dataset

We additionally provide estimated 3D human root coordinates in on the MSCOCO dataset. The coordinates are in 3D camera coordinate system, and focal lengths are set to 1500mm for both x and y axis. You can change focal length and corresponding distance using equation 2 or equation in supplementarial material of my paper.

Reference

@InProceedings{Moon_2019_ICCV_3DMPPE,
author = {Moon, Gyeongsik and Chang, Juyong and Lee, Kyoung Mu},
title = {Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image},
booktitle = {The IEEE Conference on International Conference on Computer Vision (ICCV)},
year = {2019}
}