Blur-Robust Detection via Feature Restoration: An End-to-End Framework for Prior-Guided Infrared UAV Target Detection

2025-11-18

AI Summary

Infrared UAV imagery suffers from motion blur, which degrades target contrast and severely impairs detection performance. Existing approaches treat deblurring as a standalone preprocessing step, neglecting task-aware feature enhancement. This paper proposes JFD3, an end-to-end joint deblurring and detection framework. It employs a dual-branch backbone with shared weights and introduces a frequency-structure-guided module to enable feature-level blur restoration. Moreover, it pioneers a feature-consistency self-supervised loss to jointly optimize deblurring and detection in the feature domain. Evaluated on our newly constructed IRBlurUAV dataset—comprising 30,000 synthetic and 4,118 real-world blurred infrared UAV images—JFD3 achieves significant detection accuracy gains while maintaining real-time inference speed, outperforming conventional two-stage “deblur-then-detect” pipelines.

Technology Category

• Computer Vision: Object Detection & Categorization
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Infrared unmanned aerial vehicle (UAV) target images often suffer from motion blur degradation caused by rapid sensor movement, significantly reducing contrast between target and background. Generally, detection performance heavily depends on the discriminative feature representation between target and background. Existing methods typically treat deblurring as a preprocessing step focused on visual quality, while neglecting the enhancement of task-relevant features crucial for detection. Improving feature representation for detection under blur conditions remains challenging. In this paper, we propose a novel Joint Feature-Domain Deblurring and Detection end-to-end framework, dubbed JFD3. We design a dual-branch architecture with shared weights, where the clear branch guides the blurred branch to enhance discriminative feature representation. Specifically, we first introduce a lightweight feature restoration network, where features from the clear branch serve as feature-level supervision to guide the blurred branch, thereby enhancing its distinctive capability for detection. We then propose a frequency structure guidance module that refines the structure prior from the restoration network and integrates it into shallow detection layers to enrich target structural information. Finally, a feature consistency self-supervised loss is imposed between the dual-branch detection backbones, driving the blurred branch to approximate the feature representations of the clear one. Wealso construct a benchmark, named IRBlurUAV, containing 30,000 simulated and 4,118 real infrared UAV target images with diverse motion blur. Extensive experiments on IRBlurUAV demonstrate that JFD3 achieves superior detection performance while maintaining real-time efficiency.

Problem

• Detecting infrared UAV targets degraded by motion blur
• Enhancing discriminative features for detection under blur conditions
• Integrating deblurring and detection in end-to-end framework

Innovation

• Joint feature-domain deblurring and detection framework
• Dual-branch architecture with shared weights
• Feature restoration network with clear branch guidance