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
作者PulseAugur 编辑部·[8 个来源]·
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
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…
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…
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 …
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…
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…
arXiv cs.CV
TIER_1English(EN)·Wojciech Koz{\l}owski, Rados{\l}aw Kuczba\'nski, Kamil Adamczewski, Karol Szczypkowski, Maciej Zi\k{e}ba·
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 …
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…
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…