Conditional Polarization Guidance for Camouflaged Object Detection

2026-03-31

AI Summary

Existing polarization-based camouflaged object detection methods often suffer from model complexity, high computational cost, and a failure to explicitly leverage polarization cues to guide RGB feature learning. To address these limitations, this work proposes CPGNet—a lightweight, asymmetric RGB-polarization framework that, for the first time, employs a conditional polarization guidance mechanism to dynamically modulate hierarchical RGB features. The approach further integrates a polarization edge-guided frequency-domain refinement module and an iterative feedback decoder to enable coarse-to-fine detection. Extensive experiments demonstrate that CPGNet significantly outperforms state-of-the-art methods across multiple polarized and non-polarized datasets, validating its effectiveness and strong generalization capability.

Abstract

Camouflaged object detection (COD) aims to identify targets that are highly blended with their backgrounds. Recent works have shown that the optical characteristics of polarization cues play a significant role in improving camouflaged object detection. However, most existing polarization-based approaches depend on complex visual encoders and fusion mechanisms, leading to increased model complexity and computational overhead, while failing to fully explore how polarization can explicitly guide hierarchical RGB representation learning. To address these limitations, we propose CPGNet, an asymmetric RGB-polarization framework that introduces a conditional polarization guidance mechanism to explicitly regulate RGB feature learning for camouflaged object detection. Specifically, we design a lightweight polarization interaction module that jointly models these complementary cues and generates reliable polarization guidance in a unified manner. Unlike conventional feature fusion strategies, the proposed conditional guidance mechanism dynamically modulates RGB features using polarization priors, enabling the network to focus on subtle discrepancies between camouflaged objects and their backgrounds. Furthermore, we introduce a polarization edge-guided frequency refinement strategy that enhances high-frequency components under polarization constraints, effectively breaking camouflage patterns. Finally, we develop an iterative feedback decoder to perform coarse-to-fine feature calibration and progressively refine camouflage prediction. Extensive experiments on polarization datasets across multiple tasks, along with evaluations on non-polarization datasets, demonstrate that CPGNet consistently outperforms state-of-the-art methods.

Problem

• Camouflaged Object Detection
• Polarization Guidance
• RGB Representation Learning
• Model Complexity
• Feature Fusion

Innovation

• conditional polarization guidance
• camouflaged object detection
• asymmetric RGB-polarization framework
• polarization edge-guided frequency refinement
• iterative feedback decoder