Internally Referenced Low-Light Enhancement

• URL: http://arxiv.org/abs/2605.28605v1
• Date: Wed, 27 May 2026 15:20:35 GMT
• Title: Internally Referenced Low-Light Enhancement
• Abstract summary: Self-supervised low-light image enhancement (LLIE) is highly appealing as it eliminates the reliance on external paired data.<n>We propose an Internally Referenced LLIE framework that extracts reliable physical and structural references from the degraded input image.<n>Our method achieves state-of-the-art performance, delivering superior noise suppression and textural fidelity.
• Score: 9.915987964447067
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised low-light image enhancement (LLIE) is highly appealing as it eliminates the reliance on external paired data. However, the lack of external references causes networks to struggle with decoupling entangled illumination, delicate textures, and amplified noise. To resolve this challenge, we propose an Internally Referenced LLIE framework that extracts reliable physical and structural references from the degraded input image itself. First, we introduce a local exposure-simulated scheme to extract a low-frequency pseudo ground-truth. This serves as an internal physical reference to guide global illumination estimation and correct color casts. Second, we propose a dual-domain preservation strategy with spatial and spectral constraints to construct internal structural references. Specifically, an Illumination-Aligned Perceptual loss preserves global structures under illumination shifts, while a Shift-Invariant Spectral Correlation loss captures fine-grained local structures and suppresses high-frequency noise. Finally, we propose a Gain-Adaptive Feature Modulation (GAFM) mechanism to address highly spatially-variant residual noise. By transforming the self-estimated illumination map into an internal spatial gain prior, GAFM dynamically guides a blind-spot network for spatially-aware denoising. Extensive experiments demonstrate that our method achieves state-of-the-art performance, delivering superior noise suppression and textural fidelity. Code will be publicly released at https://visonj.github.io/IRLE/.

Related papers

• NOVA-GS: Noise-Aware View-Consistent Gaussian Splatting for Low-Light Novel View Synthesis [8.990930037094982]
  NOVA-GS is a noise-aware framework for low-light 3D Gaussian Splatting.<n>It subsumes enhancement, denoising, and geometry optimization within a single process.<n>Experiments on diverse real-world low-light datasets demonstrate improved geometric fidelity, color consistency, and robustness without requiring paired supervision or well-lit references.
  arXiv  Detail & Related papers  (2026-09-11T10:26:36Z)
• LISA: Language-guided Interference-aware Spatial-Frequency Attention for Driver Gaze Estimation [12.034295331199813]
  Driver gaze estimation serves as a fundamental metric for evaluating driver attentiveness in modern monitoring systems.<n>We propose LISA, a textbfLanguage-guided textbfInterference-aware textbfSpatial-Frequency textbfAttention framework.
  arXiv  Detail & Related papers  (2026-05-17T06:57:31Z)
• ZeroIDIR: Zero-Reference Illumination Degradation Image Restoration with Perturbed Consistency Diffusion Models [72.4683657127516]
  We propose a zero-reference diffusion-based framework, named ZeroIDIR, for illumination image restoration.<n>The framework decouples the restoration process into adaptive illumination correction and diffusion-based reconstruction.<n>Experiments on publicly available benchmarks show that the proposed method outperforms state-of-the-art unsupervised competitors.
  arXiv  Detail & Related papers  (2026-05-12T02:36:49Z)
• Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework [2.977173671229414]
  We introduce Controllable Low-light Enhancement (CLE), a holistic framework supported by Light100.<n>To resolve the conflict between luminance control and chromatic fidelity, a noise-decoupled supervision strategy is employed.<n>Our approach achieves competitive performance and robust controllability, providing a real-world multi-illumination alternative.
  arXiv  Detail & Related papers  (2026-03-26T10:40:08Z)
• A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement [11.903420482259257]
  Limited illumination often causes severe physical noise and detail degradation in images.<n>Existing Low-Light Image Enhancement (LLIE) methods treat the enhancement process as a blind black-box mapping.<n>We propose a novel LLIE approach, conceptually formulated as a physics-based attack and display-adaptive defense paradigm.
  arXiv  Detail & Related papers  (2026-03-15T09:44:54Z)
• Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios [18.622785498617223]
  We propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios.<n>Our method derives a training strategy based on paired sub-images with varying illumination and noise levels.<n>In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms.
  arXiv  Detail & Related papers  (2025-03-17T12:08:52Z)
• Advancing Unsupervised Low-light Image Enhancement: Noise Estimation, Illumination Interpolation, and Self-Regulation [55.07472635587852]
  Low-Light Image Enhancement (LLIE) techniques have made notable advancements in preserving image details and enhancing contrast. These approaches encounter persistent challenges in efficiently mitigating dynamic noise and accommodating diverse low-light scenarios. We first propose a method for estimating the noise level in low light images in a quick and accurate way. We then devise a Learnable Illumination Interpolator (LII) to satisfy general constraints between illumination and input.
  arXiv  Detail & Related papers  (2023-05-17T13:56:48Z)
• Spectral Enhanced Rectangle Transformer for Hyperspectral Image Denoising [64.11157141177208]
  We propose a spectral enhanced rectangle Transformer to model the spatial and spectral correlation in hyperspectral images. For the former, we exploit the rectangle self-attention horizontally and vertically to capture the non-local similarity in the spatial domain. For the latter, we design a spectral enhancement module that is capable of extracting global underlying low-rank property of spatial-spectral cubes to suppress noise.
  arXiv  Detail & Related papers  (2023-04-03T09:42:13Z)
• Seeing Through The Noisy Dark: Toward Real-world Low-Light Image Enhancement and Denoising [125.56062454927755]
  Real-world low-light environment usually suffer from lower visibility and heavier noise, due to insufficient light or hardware limitation. We propose a novel end-to-end method termed Real-world Low-light Enhancement & Denoising Network (RLED-Net)
  arXiv  Detail & Related papers  (2022-10-02T14:57:23Z)
• Cycle-Interactive Generative Adversarial Network for Robust Unsupervised Low-Light Enhancement [109.335317310485]
  Cycle-Interactive Generative Adversarial Network (CIGAN) is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN into the generator of degradation GAN.
  arXiv  Detail & Related papers  (2022-07-03T06:37:46Z)
• Unsupervised Low-light Image Enhancement with Decoupled Networks [103.74355338972123]
  We learn a two-stage GAN-based framework to enhance the real-world low-light images in a fully unsupervised fashion. Our proposed method outperforms the state-of-the-art unsupervised image enhancement methods in terms of both illumination enhancement and noise reduction.
  arXiv  Detail & Related papers  (2020-05-06T13:37:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.