S3-CLIP: Video Super Resolution for Person-ReID

TL;DR

S3-CLIP introduces a novel video super-resolution framework for person re-identification, significantly improving tracklet quality and ranking accuracy in challenging cross-view scenarios, marking the first systematic exploration of super-resolution in this context.

Contribution

This work is the first to systematically investigate video super-resolution as a means to enhance tracklet quality for person ReID in challenging scenarios.

Findings

Achieves 37.52% mAP in aerial-to-ground scenarios.

Improves Rank-1 accuracy by 11.24% in ground-to-aerial scenarios.

Demonstrates competitive performance with baseline methods.

Abstract

Tracklet quality is often treated as an afterthought in most person re-identification (ReID) methods, with the majority of research presenting architectural modifications to foundational models. Such approaches neglect an important limitation, posing challenges when deploying ReID systems in real-world, difficult scenarios. In this paper, we introduce S3-CLIP, a video super-resolution-based CLIP-ReID framework developed for the VReID-XFD challenge at WACV 2026. The proposed method integrates recent advances in super-resolution networks with task-driven super-resolution pipelines, adapting them to the video-based person re-identification setting. To the best of our knowledge, this work represents the first systematic investigation of video super-resolution as a means of enhancing tracklet quality for person ReID, particularly under challenging cross-view conditions. Experimental results demonstrate performance competitive with the baseline, achieving 37.52% mAP in aerial-to-ground and 29.16% mAP in ground-to-aerial scenarios. In the ground-to-aerial setting, S3-CLIP achieves substantial gains in ranking accuracy, improving Rank-1, Rank-5, and Rank-10 performance by 11.24%, 13.48%, and 17.98%, respectively.