Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement

TL;DR

This paper introduces SEGD, a novel framework for infrared image enhancement that decouples complex degradations into independent processes, improving interpretability and performance over existing methods.

Contribution

The paper proposes a structural entropy-guided decoupled framework with degradation-specific modules and an evidential network, advancing infrared enhancement by better handling compound degradations.

Findings

SEGD outperforms state-of-the-art methods in infrared enhancement.

The framework achieves higher efficiency with fewer parameters.

Experimental results validate the effectiveness of the decoupled approach.

Abstract

Thermal infrared image enhancement aims to restore high-quality images from complex compound degradations. Existing all-in-one approaches typically employ a single shared backbone to handle diverse degradations, which causes gradient interference and parameter competition. To address this, we propose a Structural Entropy-Guided Decoupled (SEGD) Framework. Unlike unified modeling paradigms, SEGD decomposes compound degradations into independent sub-processes and models them in a divide-and-conquer manner through Degradation-Specific Residual Modules (DRMs). Each DRM focuses on residual estimation for a specific degradation, enabling task decoupling while remaining jointly trainable, which mitigates parameter contention. A Degradation-Aware Evidential Network further estimates degradation type and intensity, providing priors that adaptively regulate DRM restoration strength. To handle compound cases, DRMs are composed in varying orders to form multiple restoration paths, from which the most informative features are aggregated under a structural-entropy criterion, yielding decoder-ready representations with structural fidelity and degradation awareness. Integrating divide-and-conquer restoration, evidential perception, and entropy-guided adaptation, SEGD achieves fine-grained and interpretable enhancement. We also construct a nighttime TIR benchmark for evaluation under real low-light conditions. Experimental results demonstrate that SEGD surpasses state-of-the-art methods while achieving higher efficiency with fewer parameters.