RootNet of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image"
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 RootNet part.
What this repo provides:
- PyTorch implementation of Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image (ICCV 2019).
- Flexible and simple code.
- Compatibility for most of the publicly available 2D and 3D, single and multi-person pose estimation datasets including Human3.6M, MPII, MS COCO 2017, MuCo-3DHP and MuPoTS-3D.
- Human pose estimation visualization code.
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.
Directory
Root
The ${POSE_ROOT}
is described as below.
${POSE_ROOT}
|-- data
|-- common
|-- main
`-- output
data
contains data loading codes and soft links to images and annotations directories.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
| | |-- train/
| | |-- val/
| `-- annotations
|-- |-- MuCo
| `-- |-- data
| | |-- augmented_set
| | |-- unaugmented_set
| | `-- MuCo-3DHP.json
`-- |-- MuPoTS
| `-- |-- bbox
| | |-- bbox_mupots_output.json
| |-- data
| | |-- MultiPersonTestSet
| | `-- MuPoTS-3D.json
- Download Human3.6M parsed data [images][annotations]
- Download MPII parsed data [images][annotations]
- Download MuCo parsed and composited data [images_1][images_2][annotations]
- Download MuPoTS parsed parsed data [images][annotations]
- All annotation files follow MS COCO format.
- If you want to add your own dataset, you have to convert it to MS COCO format.
Output
You need to follow the directory structure of the output
folder as below.
${POSE_ROOT}
|-- output
|-- |-- log
|-- |-- model_dump
|-- |-- result
`-- |-- vis
- Creating
output
folder as soft link form is recommended instead of folder form because it would take large storage capacity. log
folder contains training log file.model_dump
folder contains saved checkpoints for each epoch.result
folder contains final estimation files generated in the testing stage.vis
folder contains visualized results.
Running 3DMPPE_ROOTNET
Start
- In the
main/config.py
, you can change settings of the model including dataset to use, network backbone, and input size and so on.
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 RootNet. Also, I provide bounding box estimations and trained models of the RootNet.
For the evaluation, you can run test.py
or there are evaluation codes in Human36M
and MuPoTS
.
Human3.6M dataset using protocol 2
Method | MRPE | MRPE_x | MRPE_y | MRPE_z |
---|---|---|---|---|
RootNet | 120.0 | 23.3 | 23.0 | 108.1 |
- Bounding box [H36M_protocol1][H36M_protocol2]
- Bounding box + 3D Human root coordinatees in camera space [H36M_protocol1][H36M_protocol2]
- RootNet model trained on H36M protocol 1 + MPII [model]
- RootNet model trained on H36M protocol 2 + MPII [model]
MuPoTS-3D dataset
Method | AP_25 |
---|---|
RootNet | 31.0 |
- Bounding box [MuPoTS-3D]
- Bounding box + 3D Human root coordinatees in camera space [MuPoTS-3D]
- RootNet model trained on MuCo-3DHP + MSCOCO [model]
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
- Bounding box + 3D Human root coordinates in camera space [MSCOCO]
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}
}