Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution

TL;DR

This paper introduces a frequency-aware dual-path framework for low-light image super-resolution, explicitly decoupling luminance and texture to improve detail restoration and structural consistency.

Contribution

The proposed DTP framework explicitly separates luminance and texture components for specialized modeling, leading to improved super-resolution performance under low-light conditions.

Findings

Achieves +1.6% PSNR and +9.6% SSIM over SOTA methods.

Reduces LPIPS by 48%, indicating better perceptual quality.

Demonstrates superior results on standard LLISR benchmarks.

Abstract

Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions with ubiquitous low-resolution devices. Although pioneer methods achieve high performance on single tasks, they solve both tasks in a serial manner, which inevitably leads to artifact amplification, texture suppression, and structural degradation. To address this, we propose Decoupling then Perceive (DTP), a novel frequency-aware framework that explicitly separates luminance and texture into semantically independent components, enabling specialized modeling and coherent reconstruction. Specifically, to adaptively separate the input into low-frequency luminance and high-frequency texture subspaces, we propose a Frequency-aware Structural Decoupling (FSD) mechanism, which lays a solid foundation for targeted representation learning and reconstruction. Based on the decoupled representation, a Semantics-specific Dual-path Representation (SDR) learning strategy that performs targeted enhancement and reconstruction for each frequency component is further designed, facilitating robust luminance adjustment and fine-grained texture recovery. To promote structural consistency and perceptual alignment in the reconstructed output, building upon this dual-path modeling, we further introduce a Cross-frequency Semantic Recomposition (CSR) module that selectively integrates the decoupled representations. Extensive experiments on the most widely used LLISR benchmarks demonstrate the superiority of our DTP framework, improving $+$1.6\% PSNR, $+$9.6\% SSIM, and $-$48\% LPIPS compared to the most state-of-the-art (SOTA) algorithm. Codes are released at https://github.com/JXVision/DTP.