Decoupled Motion Representation Learning for Moving Infrared Small Target Detection

2026-06-13

AI Summary

This work addresses the challenge of infrared small target detection in dynamic scenes, where the tight coupling among target motion, platform movement, and background dynamics hinders simultaneous achievement of high detection performance and effective false alarm suppression. To this end, we propose a decoupled motion representation learning framework that explicitly models global coherent background motion by leveraging a pretrained optical flow prior, while implicitly capturing local sparse target motion anomalies through deformable feature alignment. Furthermore, we introduce a structure-preserving self-supervised adaptation mechanism and a coherence-guided local anomaly reasoning module to effectively suppress false alarms induced by dynamic backgrounds. Evaluated on two challenging infrared small target detection benchmarks, our method significantly outperforms state-of-the-art approaches, particularly excelling in complex dynamic scenarios while maintaining computational efficiency.

Abstract

Infrared small target detection in dynamic scenes remains challenging due to the highly coupled motions among targets, imaging platforms, and dynamic backgrounds. Existing multi-frame methods usually perform implicit temporal modeling, where coherent background dynamics dominate motion correspondence learning, leading to an inherent trade-off between detection and false alarms. In this work, we observe that background motions exhibit strong global coherence, whereas small targets mainly correspond to sparse local motion anomalies. Moreover, many false-alarm responses maintain high consistency with globally coherent motion patterns, indicating that they mainly originate from coherent background dynamics rather than genuine target motions. Based on these observations, we propose a decoupled motion representation learning framework for moving infrared small target detection. Specifically, an explicit motion branch is introduced to model globally coherent motion dynamics using pretrained optical flow priors, together with a structure-preserving self-supervised adaptation strategy for infrared motion correspondence learning. Meanwhile, an implicit motion branch based on deformable feature alignment is designed to capture target-sensitive local motion anomalies under coherent motion guidance. Furthermore, a coherent-motion-guided local anomaly reasoning module is proposed to identify and suppress coherent-motion-induced false responses during localized motion modeling. Extensive experiments on two challenging infrared small target detection benchmarks demonstrate that the proposed method consistently outperforms existing state-of-the-art approaches, particularly in dynamic scenes with complex motions, while maintaining favorable inference efficiency.

Problem

• infrared small target detection
• dynamic scenes
• motion coupling
• false alarms
• motion coherence

Innovation

• Decoupled Motion Representation
• Infrared Small Target Detection
• Coherent Motion Modeling
• Local Motion Anomaly
• Optical Flow Prior