Multi-Scale Structure-Aware Network for Human Pose Estimation

TL;DR

This paper introduces a multi-scale structure-aware neural network for human pose estimation that enhances accuracy in complex scenarios involving occlusions and scale variations by integrating multi-scale supervision, structural loss, and keypoint masking.

Contribution

It presents a novel multi-scale supervision and structure-aware loss framework combined with keypoint masking to improve pose estimation accuracy under challenging conditions.

Findings

Achieved state-of-the-art results on MPII benchmark.

Effectively handles occlusions and scale variations.

Improves keypoint localization accuracy.

Abstract

We develop a robust multi-scale structure-aware neural network for human pose estimation. This method improves the recent deep conv-deconv hourglass models with four key improvements: (1) multi-scale supervision to strengthen contextual feature learning in matching body keypoints by combining feature heatmaps across scales, (2) multi-scale regression network at the end to globally optimize the structural matching of the multi-scale features, (3) structure-aware loss used in the intermediate supervision and at the regression to improve the matching of keypoints and respective neighbors to infer a higher-order matching configurations, and (4) a keypoint masking training scheme that can effectively fine-tune our network to robustly localize occluded keypoints via adjacent matches. Our method can effectively improve state-of-the-art pose estimation methods that suffer from difficulties in scale varieties, occlusions, and complex multi-person scenarios. This multi-scale supervision tightly integrates with the regression network to effectively (i) localize keypoints using the ensemble of multi-scale features, and (ii) infer global pose configuration by maximizing structural consistencies across multiple keypoints and scales. The keypoint masking training enhances these advantages to focus learning on hard occlusion samples. Our method achieves the leading position in the MPII challenge leaderboard among the state-of-the-art methods.