Direct Multi-view Multi-person 3D Human Pose Estimation

Last update: Jan 05, 2023

Related tags

Overview

Implementation of NeurIPS-2021 paper: Direct Multi-view Multi-person 3D Human Pose Estimation

[paper] [video-YouTube, video-Bilibili] [slides]

This is the official implementation of our NeurIPS-2021 work: Multi-view Pose Transformer (MvP). MvP is a simple algorithm that directly regresses multi-person 3D human pose from multi-view images.

Framework

Example Result

Reference

@article{wang2021mvp,
  title={Direct Multi-view Multi-person 3D Human Pose Estimation},
  author={Tao Wang and Jianfeng Zhang and Yujun Cai and Shuicheng Yan and Jiashi Feng},
  journal={Advances in Neural Information Processing Systems},
  year={2021}
}

1. Installation

Set the project root directory as ${POSE_ROOT}.
Install all the required python packages (with requirements.txt).
compile deformable operation for projective attention.

cd ./models/ops
sh ./make.sh

2. Data and Pre-trained Model Preparation

2.1 CMU Panoptic

Please follow VoxelPose to download the CMU Panoptic Dataset and PoseResNet-50 pre-trained model.

The directory tree should look like this:

${POSE_ROOT}
|-- models
|   |-- pose_resnet50_panoptic.pth.tar
|-- data
|   |-- panoptic
|   |   |-- 16060224_haggling1
|   |   |   |-- hdImgs
|   |   |   |-- hdvideos
|   |   |   |-- hdPose3d_stage1_coco19
|   |   |   |-- calibration_160224_haggling1.json
|   |   |-- 160226_haggling1
|   |   |-- ...

2.2 Shelf/Campus

Please follow VoxelPose to download the Shelf/Campus Dataset.

Due to the limited and incomplete annotations of the two datasets, we use psudo ground truth 3D pose generated from VoxelPose to train the model, we expect mvp would perform much better with absolute ground truth pose data.

Please use voxelpose or other methods to generate psudo ground truth for the training set, you can also use our generated psudo GT: psudo_gt_shelf. psudo_gt_campus. psudo_gt_campus_fix_gtmorethanpred.

Due to the small dataset size, we fine-tune Panoptic pre-trained model to Shelf and Campus. Download the pretrained MvP on Panoptic from model_best_5view and model_best_3view_horizontal_view or model_best_3view_2horizon_1lookdown

The directory tree should look like this:

${POSE_ROOT}
|-- models
|   |-- model_best_5view.pth.tar
|   |-- model_best_3view_horizontal_view.pth.tar
|   |-- model_best_3view_2horizon_1lookdown.pth.tar
|-- data
|   |-- Shelf
|   |   |-- Camera0
|   |   |-- ...
|   |   |-- Camera4
|   |   |-- actorsGT.mat
|   |   |-- calibration_shelf.json
|   |   |-- pesudo_gt
|   |   |   |-- voxelpose_pesudo_gt_shelf.pickle
|   |-- CampusSeq1
|   |   |-- Camera0
|   |   |-- Camera1
|   |   |-- Camera2
|   |   |-- actorsGT.mat
|   |   |-- calibration_campus.json
|   |   |-- pesudo_gt
|   |   |   |-- voxelpose_pesudo_gt_campus.pickle
|   |   |   |-- voxelpose_pesudo_gt_campus_fix_gtmorethanpred_case.pickle

2.3 Human3.6M dataset

Please follow CHUNYUWANG/H36M-Toolbox to prepare the data.

2.4 Full Directory Tree

The data and pre-trained model directory tree should look like this, you can only download the Panoptic dataset and PoseResNet-50 for reproducing the main MvP result and ablation studies:

${POSE_ROOT}
|-- models
|   |-- pose_resnet50_panoptic.pth.tar
|   |-- model_best_5view.pth.tar
|   |-- model_best_3view_horizontal_view.pth.tar
|   |-- model_best_3view_2horizon_1lookdown.pth.tar
|-- data
|   |-- pesudo_gt
|   |   |-- voxelpose_pesudo_gt_shelf.pickle
|   |   |-- voxelpose_pesudo_gt_campus.pickle
|   |   |-- voxelpose_pesudo_gt_campus_fix_gtmorethanpred_case.pickle
|   |-- panoptic
|   |   |-- 16060224_haggling1
|   |   |   |-- hdImgs
|   |   |   |-- hdvideos
|   |   |   |-- hdPose3d_stage1_coco19
|   |   |   |-- calibration_160224_haggling1.json
|   |   |-- 160226_haggling1
|   |   |-- ...
|   |-- Shelf
|   |   |-- Camera0
|   |   |-- ...
|   |   |-- Camera4
|   |   |-- actorsGT.mat
|   |   |-- calibration_shelf.json
|   |   |-- pesudo_gt
|   |   |   |-- voxelpose_pesudo_gt_shelf.pickle
|   |-- CampusSeq1
|   |   |-- Camera0
|   |   |-- Camera1
|   |   |-- Camera2
|   |   |-- actorsGT.mat
|   |   |-- calibration_campus.json
|   |   |-- pesudo_gt
|   |   |   |-- voxelpose_pesudo_gt_campus.pickle
|   |   |   |-- voxelpose_pesudo_gt_campus_fix_gtmorethanpred_case.pickle
|   |-- HM36

3. Training and Evaluation

The evaluation result will be printed after every epoch, the best result can be found in the log.

3.1 CMU Panoptic dataset

We train and validate on the five selected camera views. We trained our models on 8 GPUs and batch_size=1 for each GPU, note the total iteration per epoch should be 3205, if not, please check your data.

python -m torch.distributed.launch --nproc_per_node=8 --use_env run/train_3d.py --cfg configs/panoptic/best_model_config.yaml

Pre-trained models

Datasets	AP₂₅	AP₂₅	AP₂₅	AP₂₅	MPJPE	pth
Panoptic	92.3	96.6	97.5	97.7	15.8	here

3.1.1 Ablation Experiments

You can find several ablation experiment configs under ./configs/panoptic/, for example, removing RayConv:

python -m torch.distributed.launch --nproc_per_node=8 --use_env run/train_3d.py --cfg configs/panoptic/ablation_remove_rayconv.yaml

3.2 Shelf/Campus datasets

As shelf/campus are very small dataset with incomplete annotation, we finetune pretrained MvP with pseudo ground truth 3D pose extracted with VoxelPose, we expect more accurate GT would help MvP achieve much higher performance.

python -m torch.distributed.launch --nproc_per_node=8 --use_env run/train_3d.py --cfg configs/shelf/mvp_shelf.yaml

Pre-trained models

Datasets	Actor 1	Actor 2	Actor 2	Average	pth
Shelf	99.3	95.1	97.8	97.4	here
Campus	98.2	94.1	97.4	96.6	here

3.3 Human3.6M dataset

MvP also applies to the naive single-person setting, with dataset like Human3.6, to come

python -m torch.distributed.launch --nproc_per_node=8 --use_env run/train_3d.py --cfg configs/h36m/mvp_h36m.yaml

4. Evaluation Only

To evaluate a trained model, pass the config and model pth:

python -m torch.distributed.launch --nproc_per_node=8 --use_env run/validate_3d.py --cfg xxx --model_path xxx

LICENSE

This repo is under the Apache-2.0 license. For commercial use, please contact the authors.

Direct Multi-view Multi-person 3D Human Pose Estimation

Related tags

Overview

Implementation of NeurIPS-2021 paper: Direct Multi-view Multi-person 3D Human Pose Estimation

[paper] [video-YouTube, video-Bilibili] [slides]

Framework

Example Result

Reference

1. Installation

2. Data and Pre-trained Model Preparation

2.1 CMU Panoptic

2.2 Shelf/Campus

2.3 Human3.6M dataset

2.4 Full Directory Tree

3. Training and Evaluation

3.1 CMU Panoptic dataset

Pre-trained models

3.1.1 Ablation Experiments

3.2 Shelf/Campus datasets

Pre-trained models

3.3 Human3.6M dataset

4. Evaluation Only

LICENSE

Owner

Sea AI Lab

WaterAndScreenBreakReminders - A small python program that reminds to take a water break every 15 minutes and a screen break every 30 minutes

A pairs trade is a market neutral trading strategy enabling traders to profit from virtually any market conditions.

Python communism - A module for initiating the communist revolution in each of our python modules

This library is an abstraction for Splunk-related development, maintenance, or migration operations

A curated list of awesome things related to Pydantic! 🌪️

Just a simple python script to generate graphs of salt state requisites.

SimilarWeb for Team ACT v.0.0.1

NewsBlur is a personal news reader bringing people together to talk about the world.

PIP Manager written in python Tkinter

Curso de Python 3 do Básico ao Avançado

SciPy library main repository

Gobigger Explore For Python

Render your templates using .txt files

System Information Utility With Python

This code can help you with auto update for-TV-advertisements in the store.

Nextstrain build targeted to Omicron

Online learning platform

Metal Gear Rising: Revengeance's DAT archive (un)packer

Estimate the Market Size for Electic and Plug-In Hybrid Vehicles In Africa

Appointment Tracker that allows user to input client information and update if needed.