Decoupled Motion Representation Learning for Moving Infrared Small Target Detection
Researchers have developed a new framework for detecting small infrared targets in dynamic scenes, addressing the challenge of coupled motions between targets, imaging platforms, and backgrounds. The proposed method introduces a decoupled motion representation learning approach, separating global coherent motion dynamics from target-sensitive local motion anomalies. This framework utilizes pretrained optical flow priors and a structure-preserving self-supervised adaptation strategy for infrared motion correspondence. Experiments on benchmark datasets show that this method outperforms existing state-of-the-art approaches, particularly in complex dynamic scenes, while maintaining efficient inference. AI