From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras

TL;DR

This paper introduces an unsupervised domain adaptation method using event cameras to improve 2D human pose estimation in motion-blurred images, effectively bridging the gap between sharp and blurred domains without needing annotated data.

Contribution

It proposes a novel approach leveraging event cameras and a student-teacher framework with uncertainty masking for robust pose estimation under motion blur.

Findings

Outperforms conventional domain-adaptive methods in motion blur scenarios

Achieves robust pose estimation without target domain annotations

Demonstrates effectiveness of event-based augmentation for domain adaptation

Abstract

Human pose estimation is critical for applications such as rehabilitation, sports analytics, and AR/VR systems. However, rapid motion and low-light conditions often introduce motion blur, significantly degrading pose estimation due to the domain gap between sharp and blurred images. Most datasets assume stable conditions, making models trained on sharp images struggle in blurred environments. To address this, we introduce a novel domain adaptation approach that leverages event cameras, which capture high temporal resolution motion data and are inherently robust to motion blur. Using event-based augmentation, we generate motion-aware blurred images, effectively bridging the domain gap between sharp and blurred domains without requiring paired annotations. Additionally, we develop a student-teacher framework that iteratively refines pseudo-labels, leveraging mutual uncertainty masking to eliminate incorrect labels and enable more effective learning. Experimental results demonstrate that our approach outperforms conventional domain-adaptive human pose estimation methods, achieving robust pose estimation under motion blur without requiring annotations in the target domain. Our findings highlight the potential of event cameras as a scalable and effective solution for domain adaptation in real-world motion blur environments. Our project codes are available at https://github.com/kmax2001/EvSharp2Blur.