MeTRAbs Absolute 3D Human Pose Estimator

This repository contains code for the methods described in the following paper:

MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
by István Sárándi, Timm Linder, Kai O. Arras, Bastian Leibe
IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM), Selected Best Works From Automated Face and Gesture Recognition 2020

News

[2021-10-19] Released new best-performing models based on EfficientNetV2 and super fast ones using MobileNetV3, simplified API, multiple skeleton conventions, support for radial/tangential distortion, improved antialiasing, plausibility filtering and other new features.
[2021-10-19] Full codebase migrated to TensorFlow 2 and Keras
[2020-11-19] Oral presentation at the IEEE Conference on Automatic Face and Gesture Recognition (FG'20) (Talk Video and Slides)
[2020-11-16] Training and evaluation code now released along with dataset pre-processing scripts! Code and models upgraded to Tensorflow 2.
[2020-10-06] Journal paper accepted for publication in the IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM), Best of FG Special Issue
[2020-08-23] Short presentation at ECCV2020's 3DPW workshop (slides)
[2020-08-06] Our method has won the 3DPW Challenge

Inference Code

We release standalone TensorFlow models (SavedModel) to allow easy application in downstream research. After loading the model, you can run inference in a single line of Python without having this codebase as a dependency. Try it in action in Google Colab.

Gist of Usage

import tensorflow as tf

model = tf.saved_model.load('path/to/metrabs_eff2l_y4')
image = tf.image.decode_jpeg(tf.io.read_file('img/test_image_3dpw.jpg'))
pred = model.detect_poses(image)
pred['boxes'], pred['poses2d'], pred['poses3d']

NOTE: The models can only be used for non-commercial purposes due to the licensing of the used training datasets.

Demos

./demo.py to auto-download the model, predict on a sample image and display the result with Matplotlib or PoseViz (if installed).
./demo_webcam.py to show webcam inference with the MobileNetV3 backbone (fast but lower accuracy, requires PoseViz).
./demo_video_batched.py path/to/video.mp4 to run batched video inference (requires PoseViz).

Documentation

Feature Summary

Several skeleton conventions supported through the keyword argument skeleton (e.g. COCO, SMPL, H36M)
Multi-image (batched) and single-image predictions both supported
Advanced, parallelized cropping logic behind the scenes
- Anti-aliasing through image pyramid and supersampling, gamma-correct rescaling.
- GPU-accelerated undistortion of pinhole perspective (homography) and radial/tangential lens distortions
Estimates returned in 3D world space (when calibration is provided) and 2D pixel space
Built-in, configurable test-time augmentation (TTA) with rotation, flip and brightness (keyword argument num_aug sets the number of TTA crops per detection)
Automatic suppression of implausible poses and non-max suppression on the 3D pose level (can be turned off)
Multiple backbones with different speed-accuracy trade-off (EfficientNetV2, MobileNetV3)

Training and Evaluation

See the docs on training and evaluation to perform the experiments presented in the paper.

BibTeX

If you find this work useful in your research, please cite it as:

@article{sarandi2021metrabs,
  title={{MeTRAbs:} Metric-Scale Truncation-Robust Heatmaps for Absolute 3{D} Human Pose Estimation},
  author={S\'ar\'andi, Istv\'an and Linder, Timm and Arras, Kai O. and Leibe, Bastian},
  journal={IEEE Transactions on Biometrics, Behavior, and Identity Science},
  year={2021},
  volume={3},
  number={1},
  pages={16-30},
  doi={10.1109/TBIOM.2020.3037257}
}

The above paper is an extended journal version of the FG'2020 conference paper:

@inproceedings{Sarandi20FG,
  title={Metric-Scale Truncation-Robust Heatmaps for 3{D} Human Pose Estimation},
  author={S\'ar\'andi, Istv\'an and Linder, Timm and Arras, Kai O. and Leibe, Bastian},
  booktitle={IEEE International Conference on Automatic Face and Gesture Recognition},
  pages={677-684},
  year={2020}
}

Contact

Code in this repository was written by István Sárándi (RWTH Aachen University) unless indicated otherwise.

Got any questions or feedback? Drop a mail to sarandi@vision.rwth-aachen.de!

Eng-Youssef/metrabs