Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?

TL;DR

This paper investigates whether super resolution techniques can enhance human pose estimation accuracy in low-resolution images, proposing a novel method that adapts SR application based on individual segmentation size.

Contribution

The study demonstrates that applying super resolution improves pose estimation for small, low-resolution subjects and introduces a Mask-RCNN based adaptive approach for optimal SR use.

Findings

SR improves keypoint detection for small, low-resolution people

Performance gain depends on initial pixel count of subjects

Adaptive Mask-RCNN approach yields best results on low-res datasets

Abstract

The results obtained from state of the art human pose estimation (HPE) models degrade rapidly when evaluating people of a low resolution, but can super resolution (SR) be used to help mitigate this effect? By using various SR approaches we enhanced two low resolution datasets and evaluated the change in performance of both an object and keypoint detector as well as end-to-end HPE results. We remark the following observations. First we find that for people who were originally depicted at a low resolution (segmentation area in pixels), their keypoint detection performance would improve once SR was applied. Second, the keypoint detection performance gained is dependent on that persons pixel count in the original image prior to any application of SR; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger. To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step. This approach achieved the best results on our low resolution datasets for each HPE performance metrics.