UniPose: Unified Human Pose Estimation in Single Images and Videos

Bruno Artacho, Andreas Savakis
1/22/2020
cs.CV

Official code: bmartacho/UniPose (223 stars, last commit 2022-06-06).

Abstract

We propose UniPose, a unified framework for human pose estimation, based on our "Waterfall" Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual segmentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Additionally, our method is extended to UniPose-LSTM for multi-frame processing and achieves state-of-the-art results for temporal pose estimation in Video. Our results on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of-the-art results in single person pose detection for both single images and videos.

View on arXivView PDF

Code Implementations(1)

bmartacho/UniPoseOfficial100%

We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.

22346PythonJan 22, 20204 years agoNOASSERTION

Similar Papers

Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature Fusion

91% match1 repo312025

An End-to-End Framework for Video Multi-Person Pose Estimation

88% match2025

End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer

88% match1 repo252025

GateAttentionPose: Enhancing Pose Estimation with Agent Attention and Improved Gated Convolutions

88% match2024

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

88% match1 repo832023

Towards High Performance One-Stage Human Pose Estimation

88% match2023

Cite this paper

@article{artacho2020unipose,
  title  = {UniPose: Unified Human Pose Estimation in Single Images and Videos},
  author = {Bruno Artacho and Andreas Savakis},
  year   = {2020},
  eprint = {2001.08095},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2001.08095}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2001.08095.svg)](https://codeofpaper.com/paper/2001.08095)

Discussion