Enlight: Fast Low-Light Image Enhancement via Multi-Objective Optimization and Shadow-Aware Refinement

• URL: http://arxiv.org/abs/2606.21674v1
• Date: Fri, 19 Jun 2026 18:29:24 GMT
• Title: Enlight: Fast Low-Light Image Enhancement via Multi-Objective Optimization and Shadow-Aware Refinement
• Abstract summary: We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of an objective.<n>Unlike deep learning approaches that require large scale training data and supervision, ENLIGHT operates in a zero-shot manner by optimizing image quality at inference time.
• Score: 0.48495505229708397
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present ENLIGHT, a fast and training free framework for low-light image enhancement based on direct optimization of a perceptual objective. Unlike deep learning approaches that require large scale training data and supervision, ENLIGHT operates in a zero-shot manner by optimizing image quality at inference time. The method employs a two stage global to local optimization strategy. In the first stage, ENLIGHT performs global illumination adjustment to improve visibility while maintaining structural consistency and avoiding excessive noise enhancement. In the second stage, a shadow aware refinement selectively improves low-intensity regions through masked local optimization, enhancing visibility without overexposure. To balance quality and efficiency, we introduce two modes: Fast, which uses a multi-objective formulation combining entropy, gradient preservation, and noise regularization, and Ultrafast, which reduces computational cost via a lightweight approximation of the same objective. The framework is optimizer agnostic and supports both evolutionary and lightweight local search methods. Experiments on BAID, Backlit300, LIME, MEF, NPE, and DICM demonstrate that ENLIGHT achieves competitive perceptual quality (MUSIQ, NIQE, BRISQUE) with significantly lower inference time. Qualitative results further show improved contrast, preserved structural details, and controlled noise amplification, making ENLIGHT a practical and interpretable alternative to learning based methods.

Related papers

• UBLLIE: Unified Backlight and Low-Light Image Enhancement [15.386282490743838]
  Backlit and low-light images often suffer from severe exposure imbalance or global underexposure.<n>We propose a unified, unsupervised enhancement framework that addresses both types of degradation.<n>Our framework consistently outperforms state-of-the-art supervised and unsupervised methods in terms of fidelity, perceptual quality, and generalization.
  arXiv  Detail & Related papers  (2026-08-05T04:17:05Z)
• 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)
• FLARE-BO: Fused Luminance and Adaptive Retinex Enhancement via Bayesian Optimisation for Low-Light Robotic Vision [3.490087692799367]
  This paper proposes FLARE-BO, an extended framework that jointly optimises eight parameters spanning across gamma correction, LIME-style illumination normalisation, chrominance denoising, bilateral filtering, NLM denoising, Grey-World automatic white balance, and adaptive post smoothing.<n>Results show marked improvements of the proposed method over existing methods that were not specifically trained using this dataset.
  arXiv  Detail & Related papers  (2026-04-23T21:51:22Z)
• LightQANet: Quantized and Adaptive Feature Learning for Low-Light Image Enhancement [65.06462316546806]
  Low-light image enhancement aims to improve illumination while preserving high-quality color and texture.<n>Existing methods often fail to extract reliable feature representations due to severely degraded pixel-level information under low-light conditions.<n>We propose LightQANet, a novel framework that introduces quantized and adaptive feature learning for low-light enhancement.
  arXiv  Detail & Related papers  (2025-10-16T14:54:42Z)
• Striving for Faster and Better: A One-Layer Architecture with Auto Re-parameterization for Low-Light Image Enhancement [50.93686436282772]
  We aim to delve into the limits of image enhancers both from visual quality and computational efficiency.<n>By rethinking the task demands, we build an explicit connection, i.e., visual quality and computational efficiency are corresponding to model learning and structure design.<n>Ultimately, this achieves efficient low-light image enhancement using only a single convolutional layer, while maintaining excellent visual quality.
  arXiv  Detail & Related papers  (2025-02-27T08:20:03Z)
• Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors [38.96909959677438]
  Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources. We devise a novel unsupervised LIE framework based on diffusion priors and lookup tables to achieve efficient low-light image recovery.
  arXiv  Detail & Related papers  (2024-09-27T16:37:27Z)
• ALEN: A Dual-Approach for Uniform and Non-Uniform Low-Light Image Enhancement [10.957431540794836]
  Inadequate illumination can lead to significant information loss and poor image quality, impacting various applications such as surveillance.<n>Current enhancement techniques often use specific datasets to enhance low-light images, but still present challenges when adapting to diverse real-world conditions.<n>The Adaptive Light Enhancement Network (ALEN) is introduced, whose main approach is the use of a classification mechanism to determine whether local or global illumination enhancement is required.
  arXiv  Detail & Related papers  (2024-07-29T05:19:23Z)
• Learning a Single Convolutional Layer Model for Low Light Image Enhancement [43.411846299085575]
  Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. A single convolutional layer model (SCLM) is proposed that provides global low-light enhancement as the coarsely enhanced results. Experimental results demonstrate that the proposed method performs favorably against the state-of-the-art LLIE methods in both objective metrics and subjective visual effects.
  arXiv  Detail & Related papers  (2023-05-23T13:12:00Z)
• 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)
• Gap-closing Matters: Perceptual Quality Evaluation and Optimization of Low-Light Image Enhancement [55.8106019031768]
  There is a growing consensus in the research community that the optimization of low-light image enhancement approaches should be guided by the visual quality perceived by end users. We propose a gap-closing framework for assessing subjective and objective quality systematically. We validate the effectiveness of our proposed framework through both the accuracy of quality prediction and the perceptual quality of image enhancement.
  arXiv  Detail & Related papers  (2023-02-22T15:57:03Z)
• The Loop Game: Quality Assessment and Optimization for Low-Light Image Enhancement [17.874116769066095]
  There is an increasing consensus that the design and optimization of low light image enhancement methods need to be fully driven by perceptual quality.<n>We propose a loop enhancement framework that produces a clear picture of how the enhancement of low-light images could be optimized towards better visual quality.
  arXiv  Detail & Related papers  (2022-02-20T06:20:06Z)
• CERL: A Unified Optimization Framework for Light Enhancement with Realistic Noise [81.47026986488638]
  Low-light images captured in the real world are inevitably corrupted by sensor noise. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded framework.
  arXiv  Detail & Related papers  (2021-08-01T15:31:15Z)
• 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.