OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation

TL;DR

OmniPose is an end-to-end multi-scale framework for multi-person pose estimation that achieves state-of-the-art accuracy by leveraging a novel waterfall module and multi-scale features without post-processing.

Contribution

It introduces a waterfall module for multi-scale feature extraction, improving pose estimation accuracy and efficiency without requiring post-processing steps.

Findings

Achieves state-of-the-art results on multiple datasets.

Utilizes a novel waterfall module for multi-scale features.

Maintains efficiency comparable to spatial pyramid methods.

Abstract

We propose OmniPose, a single-pass, end-to-end trainable framework, that achieves state-of-the-art results for multi-person pose estimation. Using a novel waterfall module, the OmniPose architecture leverages multi-scale feature representations that increase the effectiveness of backbone feature extractors, without the need for post-processing. OmniPose incorporates contextual information across scales and joint localization with Gaussian heatmap modulation at the multi-scale feature extractor to estimate human pose with state-of-the-art accuracy. The multi-scale representations, obtained by the improved waterfall module in OmniPose, leverage the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Our results on multiple datasets demonstrate that OmniPose, with an improved HRNet backbone and waterfall module, is a robust and efficient architecture for multi-person pose estimation that achieves state-of-the-art results.