Saved in:
Bibliographic Details
Main Authors: He, Ji-Xuan, Zhao, Jia-Cheng, Cui, Feng-Qi, Huang, Jinyang, Liu, Yang, Zhao, Sirui, Li, Meng, Liu, Zhi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27301
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914429504847872
author He, Ji-Xuan
Zhao, Jia-Cheng
Cui, Feng-Qi
Huang, Jinyang
Liu, Yang
Zhao, Sirui
Li, Meng
Liu, Zhi
author_facet He, Ji-Xuan
Zhao, Jia-Cheng
Cui, Feng-Qi
Huang, Jinyang
Liu, Yang
Zhao, Sirui
Li, Meng
Liu, Zhi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27301
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution
He, Ji-Xuan
Zhao, Jia-Cheng
Cui, Feng-Qi
Huang, Jinyang
Liu, Yang
Zhao, Sirui
Li, Meng
Liu, Zhi
Computer Vision and Pattern Recognition
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.
title Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.27301