Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Ji-Xuan He, Jia-Cheng Zhao, Feng-Qi Cui, Jinyang Huang, Yang Liu, Sirui Zhao, Meng Li, Zhi Liu

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.

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

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.

Paper Structure

This paper contains 21 sections, 4 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Frequency-aware Structural Decomposition
  4. Semantics-specific Dual-path Representation
  5. Luminance Enhancement via Bio-inspired Activation
  6. Texture Restoration via Residual-based Hierarchical Denoising
  7. Cross-frequency Semantic Recomposition
  8. Experiments
  9. Experiment Settings
  10. Datasets
  11. Validation Metrics
  12. Implementation Details
  13. Comparison with State-of-the-Artst Methods
  14. Visualization
  15. Qualitative Visualization
  16. ...and 6 more sections

Figures (4)

  • Figure 1: Comparison of existing methods and our proposed approach. (a) and (b) represent sequential and joint spatial-domain LLISR methods, respectively, which suffer from uneven luminance and blurred textures due to early-stage semantic entanglement. (c) illustrates our frequency-aware disentanglement strategy, which explicitly separates and models luminance and texture components, enabling faithful recovery with both crisp luminance and fine textures.
  • Figure 2: An overview of the proposed DTP (a) The overall processing flow of DTP. (b) The pipeline of Decoupling Stage (FSD) in DTP. (c) The flow of Representation Specialization Stage (SDR). (d) The sketch of Fusion and Reconstruction Stage (CSR).
  • Figure 3: Qualitative comparisons of $\times$2 tasks on RELLISUR. The top row shows the full restored images, the middle displays zoomed-in patches for local structure inspection, and the bottom presents RGB histogram distributions.
  • Figure 4: Visual comparison under extreme low-light conditions ($-2.5$ EV to $-4.5$ EV) on the RELLISUR dataset.