PulseAugur
实时 21:38:09
English(EN) Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective

新AI方法提升低光图像增强效果,侧重效率和移动端部署

研究人员开发了一个统一的图像增强框架,将近期方法归类为三种连续时间过程:无条件扩散模型、Ornstein-Uhlenbeck过程和扩散桥。这种统一表明,这些方法之间的差异源于它们的漂移项和扩散项、终端分布以及边界条件,而非调度器或采样器。一项跨越各种图像增强任务的实证研究表明,没有一种方法能持续占优,这凸显了特定设计选择的影响。此外,一项专注于移动设备高效低光图像增强的挑战赛吸引了大量参与,旨在平衡增强质量与计算效率,以实现实际部署。 AI

影响 图像增强技术的进步,特别是在低光条件和移动设备方面,有望提高各种应用中的视觉质量。

排序理由 多篇arXiv论文详细介绍了新的研究,以及一项专注于图像增强技术的挑战赛。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →

新AI方法提升低光图像增强效果,侧重效率和移动端部署

报道来源 [8]

  1. arXiv cs.AI TIER_1 English(EN) · Ahmed Cherif ·

    BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement

    Low-light image enhancement is a fundamental challenge in computer vision and multimedia applications, as images captured under insufficient illumination suffer from poor visibility, low contrast, and color distortion. Existing Retinex-based methods rely on manually tuned paramet…

  2. arXiv cs.CV TIER_1 English(EN) · Ahmed Cherif ·

    BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement

    arXiv:2605.03509v1 Announce Type: new Abstract: Low-light image enhancement is a fundamental challenge in computer vision and multimedia applications, as images captured under insufficient illumination suffer from poor visibility, low contrast, and color distortion. Existing Reti…

  3. arXiv cs.CV TIER_1 English(EN) · Jiebin Yan, Chenyu Tu, Weixia Zhang, Zhihua Wang, Peibei Cao, Qinghua Lin, Yuming Fang, Xiaoning Liu, Zongwei Wu, Zhuyun Zhou, Radu Timofte ·

    NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results

    arXiv:2605.02212v1 Announce Type: new Abstract: This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This challenge focuses on mobile image enhancement under …

  4. arXiv cs.CV TIER_1 English(EN) · Guangrui Bai, Hailong Yan, Wenhai Liu, Yahui Deng, Erbao Dong ·

    Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices

    arXiv:2507.04277v2 Announce Type: replace Abstract: Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, lim…

  5. arXiv cs.CV TIER_1 English(EN) · Guangrui Bai, Yifan Mei, Yahui Deng, Yuhan Chen, Yuze Qiu, Wenhai Liu, Erbao Dong ·

    Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective

    arXiv:2605.02627v1 Announce Type: new Abstract: Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the pro…

  6. arXiv cs.CV TIER_1 English(EN) · Wojciech Koz{\l}owski, Rados{\l}aw Kuczba\'nski, Kamil Adamczewski, Karol Szczypkowski, Maciej Zi\k{e}ba ·

    Unifying Deep Stochastic Processes for Image Enhancement

    arXiv:2605.01568v1 Announce Type: new Abstract: Deep stochastic processes have recently become a central paradigm for image enhancement, with many methods explicitly conditioning the stochastic trajectory on the degraded input. However, the relationship between these conditional …

  7. arXiv cs.CV TIER_1 English(EN) · Erbao Dong ·

    Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective

    Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromatic noise. Experiments on LOLv2-Real, MIT-Adobe FiveK, and LSRW show that the proposed method achieves competitive or superior qu…

  8. arXiv cs.CV TIER_1 English(EN) · Radu Timofte ·

    NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results

    This paper presents a comprehensive review of the NITRE 2026 Efficient Low Light Image Enhancement (E-LLIE) Challenge, highlighting the proposed solutions and final outcomes. This challenge focuses on mobile image enhancement under low-light conditions, aiming to design lightweig…