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

TB Set color display - Add-on for Blender to set multiple objects and material Display Color at once.

Excel cell checker with python

Este script añade la config de s4vitar a bspwm automaticamente!

Clock in automatically in SCU.

Cairo-bloom - A naive bloom filter implementation in Cairo

Script to calculate the italian fiscal code of a person.

Project Faros is a reference implimentation of Red Hat OpenShift 4 on small footprint, bare-metal clusters.

Personal Assistant Tessa

Script para generar automatización de registro de formularios IEEH

Python template for Advent of Code event

Buildium-to-stessa - Automation to assist in converting Buildium transactions into Stessa format

A webdav demo using a virtual filesystem that serves a random status of whether a cat in a box is dead or alive.

School helper, helps you at your pyllabus's.

Hacktoberfest2021 🥳- Contribute Any Pattern In Any Language😎 Every PR will be accepted Pls contribute

CHIP-8 interpreter written in Python

A very simple boarding app with DRF

A collection of examples of using cocotb for functional verification of VHDL designs with GHDL.

PyMedPhys is an open-source Medical Physics python library

Data on Free Food at MIT

An implementation of Ray Tracing in One Weekend using Taichi