[BMVC2021] "TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation"

Last update: Dec 23, 2022

Overview

TransFusion-Pose

TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
Haoyu Ma, Liangjian Chen, Deying Kong, Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin and Xiaohui Xie
In BMVC 2021
[Paper] [Video]

Overview

We propose the TransFusion, which apply the transformer architecture to multi-view 3D human pose estimation
We propose the Epipolar Field, a novel and more general form of epipolar line. It readily integrates with the transformer through our proposed geometry positional encoding to encode the 3D relationships among different views.
Extensive experiments are conducted to demonstrate that our TransFusion outperforms previous fusion methods on both Human 3.6M and SkiPose datasets, but requires substantially fewer parameters.

Installation

Clone this repo, and we'll call the directory that you cloned multiview-pose as ${POSE_ROOT}

git clone https://github.com/HowieMa/TransFusion-Pose.git

Install dependencies.

pip install -r requirements.txt

Download TransPose models pretrained on COCO.

wget https://github.com/yangsenius/TransPose/releases/download/Hub/tp_r_256x192_enc3_d256_h1024_mh8.pth

You can also download it from the official website of TransPose

Please download them under ${POSE_ROOT}/models, and make them look like this:

${POSE_ROOT}/models
└── pytorch
    └── coco
        └── tp_r_256x192_enc3_d256_h1024_mh8.pth

Data preparation

Human 3.6M

For Human36M data, please follow H36M-Toolbox to prepare images and annotations.

Ski-Pose

For Ski-Pose, please follow the instruction from their website to obtain the dataset.
Once you download the Ski-PosePTZ-CameraDataset-png.zip and ski_centers.csv, unzip them and put into the same folder, named as ${SKI_ROOT}.
Run python data/preprocess_skipose.py ${SKI_ROOT} to format it.

Your folder should look like this:

${POSE_ROOT}
|-- data
|-- |-- h36m
    |-- |-- annot
        |   |-- h36m_train.pkl
        |   |-- h36m_validation.pkl
        |-- images
            |-- s_01_act_02_subact_01_ca_01 
            |-- s_01_act_02_subact_01_ca_02

|-- |-- preprocess_skipose.py
|-- |-- skipose  
    |-- |-- annot
        |   |-- ski_train.pkl
        |   |-- ski_validation.pkl
        |-- images
            |-- seq_103 
            |-- seq_103

Training and Testing

Human 3.6M

# Training
python run/pose2d/train.py --cfg experiments-local/h36m/transpose/256_fusion_enc3_GPE.yaml --gpus 0,1,2,3

# Evaluation (2D)
python run/pose2d/valid.py --cfg experiments-local/h36m/transpose/256_fusion_enc3_GPE.yaml --gpus 0,1,2,3  

# Evaluation (3D)
python run/pose3d/estimate_tri.py --cfg experiments-local/h36m/transpose/256_fusion_enc3_GPE.yaml

Ski-Pose

# Training
python run/pose2d/train.py --cfg experiments-local/skipose/transpose/256_fusion_enc3_GPE.yaml --gpus 0,1,2,3

# Evaluation (2D)
python run/pose2d/valid.py --cfg experiments-local/skipose/transpose/256_fusion_enc3_GPE.yaml --gpus 0,1,2,3

# Evaluation (3D)
python run/pose3d/estimate_tri.py --cfg experiments-local/skipose/transpose/256_fusion_enc3_GPE.yaml

Our trained models can be downloaded from here

Citation

If you find our code helps your research, please cite the paper:

@inproceedings{ma2021transfusion,
  title={TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation},
  author={Ma, Haoyu and Chen, Liangjian and Kong, Deying and Wang, Zhe and Liu, Xingwei and Tang, Hao and Yan, Xiangyi and Xie, Yusheng and Lin, Shih-Yao and Xie, Xiaohui},
  booktitle={British Machine Vision Conference},
  year={2021}
}

[BMVC2021] "TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation"

Related tags

Overview

TransFusion-Pose

Overview

Installation

Data preparation

Human 3.6M

Ski-Pose

Training and Testing

Human 3.6M

Ski-Pose

Citation

Acknowledgement

Owner

Haoyu Ma

pytorch implementation of fast-neural-style

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

Official implementation of the paper Do pedestrians pay attention? Eye contact detection for autonomous driving

This repo is for segmentation of T2 hyp regions in gliomas.

【CVPR 2021, Variational Inference Framework, PyTorch】 From Rain Generation to Rain Removal

StyleGAN-Human: A Data-Centric Odyssey of Human Generation

Creating Multi Task Models With Keras

How to Train a GAN? Tips and tricks to make GANs work

DWIPrep is a robust and easy-to-use pipeline for preprocessing of diverse dMRI data.

No Code AI/ML platform

Inverse Optimal Control Adapted to the Noise Characteristics of the Human Sensorimotor System

RCDNet: A Model-driven Deep Neural Network for Single Image Rain Removal (CVPR2020)

Official PyTorch implementation for paper "Efficient Two-Stage Detection of Human–Object Interactions with a Novel Unary–Pairwise Transformer"

Unsupervised Foreground Extraction via Deep Region Competition

RL Algorithms with examples in Python / Pytorch / Unity ML agents

The code from the paper Character Transformations for Non-Autoregressive GEC Tagging

An implementation for `Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extraction`

Python-experiments - A Repository which contains python scripts to automate things and make your life easier with python

Generate saved_model, tfjs, tf-trt, EdgeTPU, CoreML, quantized tflite and .pb from .tflite.

Code for the paper "Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds" (ICCV 2021)