Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework

• URL: http://arxiv.org/abs/2603.25296v1
• Date: Thu, 26 Mar 2026 10:40:08 GMT
• Title: Towards Controllable Low-Light Image Enhancement: A Continuous Multi-illumination Dataset and Efficient State Space Framework
• Abstract summary: 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.
• Score: 2.977173671229414
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-light image enhancement (LLIE) has traditionally been formulated as a deterministic mapping. However, this paradigm often struggles to account for the ill-posed nature of the task, where unknown ambient conditions and sensor parameters create a multimodal solution space. Consequently, state-of-the-art methods frequently encounter luminance discrepancies between predictions and labels, often necessitating "gt-mean" post-processing to align output luminance for evaluation. To address this fundamental limitation, we propose a transition toward Controllable Low-light Enhancement (CLE), explicitly reformulating the task as a well-posed conditional problem. To this end, we introduce CLE-RWKV, a holistic framework supported by Light100, a new benchmark featuring continuous real-world illumination transitions. To resolve the conflict between luminance control and chromatic fidelity, a noise-decoupled supervision strategy in the HVI color space is employed, effectively separating illumination modulation from texture restoration. Architecturally, to adapt efficient State Space Models (SSMs) for dense prediction, we leverage a Space-to-Depth (S2D) strategy. By folding spatial neighborhoods into channel dimensions, this design allows the model to recover local inductive biases and effectively bridge the "scanning gap" inherent in flattened visual sequences without sacrificing linear complexity. Experiments across seven benchmarks demonstrate that our approach achieves competitive performance and robust controllability, providing a real-world multi-illumination alternative that significantly reduces the reliance on gt-mean post-processing.

Related papers

• AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement [19.712825613823778]
  This paper proposes an Adaptive Illumination Gaussian Splatting Network (AIGS-Net) for fast low-light enhancement.<n>Unlike conventional static priors, AIGS-Net constructs an input-adaptive 2D Gaussian Splatting illumination field.<n>Experiments show that AIGS-Net improves detail recovery and color fidelity while requiring only approximately 40 learnable parameters.
  arXiv  Detail & Related papers  (2026-06-16T14:45:55Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Benchmarking Visual Feature Representations for LiDAR-Inertial-Visual Odometry Under Challenging Conditions [11.85572971097983]
  This paper introduces a hybrid approach that integrates direct photometric methods with descriptor-based feature matching.<n>The experimental results reveal that the proposed hybrid approach outperforms the conventional sparse-direct method.
  arXiv  Detail & Related papers  (2026-03-19T07:56:49Z)
• Anchor then Polish for Low-light Enhancement [10.471765109354724]
  Low-light image enhancement is challenging due to entangled degradations.<n>This work proposes a novel anchor-then-polish (ATP) framework to fundamentally decouple global energy alignment from local detail refinement.<n>Our method achieves state-of-the-art performance, producing visually natural and quantitatively superior low-light enhancements.
  arXiv  Detail & Related papers  (2026-03-16T16:06:30Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation [18.67176370944511]
  Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges.<n>We propose a generative framework based on visual autoregressive ( VAR) modeling, guided by perceptual priors from the vision-language model (VLM)<n>Our framework is fully unsupervised and achieves state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-23T19:08:45Z)
• Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement [31.996801376824408]
  Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization.<n>This paper introduces Luminance-Aware Statistical Quantification (LASQ), a novel framework that reformulates LLIE as a statistical sampling process over hierarchical luminance distributions.<n>LASQ re-conceptualizes luminance transition as a power-law distribution in intensity coordinate space that can be approximated by stratified power functions.
  arXiv  Detail & Related papers  (2025-11-03T12:24:52Z)
• Veila: Panoramic LiDAR Generation from a Monocular RGB Image [18.511014983119274]
  Realistic and controllable panoramic LiDAR data generation is critical for scalable 3D perception in autonomous driving and robotics.<n>Leveraging a monocular RGB image as a spatial control signal offers a scalable and low-cost alternative.<n>We propose Veila, a novel conditional diffusion framework that integrates semantic and depth cues according to their local reliability.
  arXiv  Detail & Related papers  (2025-08-05T17:59:53Z)
• SAIGFormer: A Spatially-Adaptive Illumination-Guided Network for Low-Light Image Enhancement [58.79901582809091]
  Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>Recent Transformer-based low-light enhancement methods have made promising progress in recovering global illumination.<n>We present a Spatially-Adaptive Illumination-Guided Transformer framework that enables accurate illumination restoration.
  arXiv  Detail & Related papers  (2025-07-21T11:38:56Z)
• Towards Generalized Range-View LiDAR Segmentation in Adverse Weather [65.22588361803942]
  We identify and analyze the unique challenges that affect the generalization of range-view LiDAR segmentation in severe weather.<n>We propose a modular and lightweight framework that enhances robustness without altering the core architecture of existing models.<n>Our approach significantly improves generalization to adverse weather with minimal inference overhead.
  arXiv  Detail & Related papers  (2025-06-10T16:48:27Z)
• Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition [52.89441679581216]
  Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise.<n>We present an innovative video decomposition strategy that incorporates view-independent and view-dependent components.<n>Our framework consistently outperforms existing methods, establishing a new SOTA performance.
  arXiv  Detail & Related papers  (2024-05-24T15:56:40Z)
• Diving into Darkness: A Dual-Modulated Framework for High-Fidelity Super-Resolution in Ultra-Dark Environments [51.58771256128329]
  This paper proposes a specialized dual-modulated learning framework that attempts to deeply dissect the nature of the low-light super-resolution task. We develop Illuminance-Semantic Dual Modulation (ISDM) components to enhance feature-level preservation of illumination and color details. Comprehensive experiments showcases the applicability and generalizability of our approach to diverse and challenging ultra-low-light conditions.
  arXiv  Detail & Related papers  (2023-09-11T06:55:32Z)
• 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)

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.