u014546828的博客

具体而言，将x_i的第c个通道记为x_ic（属于第g组），通过N_{K_S}(x_ic)与w^∗_ig∈R^{K_S×K_S}的卷积运算获得其聚合特征表示y_ic。LS卷积的计算主要包含三部分：P_ls中的逐点卷积、P_ls中K_L×K_L的深度卷积，以及A_ls中K_S×K_S的卷积聚合。​（N_{K_L}(x_i)表示以x_i为中心的K_L×K_L邻域）。{K_S}(x_i)**​（表示以x_i为中心的K_S×K_S邻域）。，其上下文区域是以x_i为中心的K×K邻域，记为N_K(x_i)。

https://arxiv.org/pdf/2408.07932GitHubLucas Nedel Kirsten, Zhicheng Fu, Nikhil Ambha MadhusudhanaRecent advances in camera design and imaging technology have enabled the capture of high-quality images using smartphones. However, due to the limited dynamic

本文提出：自校准照明 (Self-Calibrated Illumination，SCI) 学习框架，快速、灵活、鲁棒性好。SCI 模型在基于网络的微光图像增强领域重新定义了视觉质量、计算效率和下游任务性能的峰值点。

本文采用强化学习实现图像编辑，问题与方法契合度很高，因此是一个不错的思路。人为的图像编辑通常是采取不同操作[pdf]Fig. 1. Our method provides automatic and end-to-end processing of RAW photos, directly from linear RGB data captured by camera sensors to visually pleasing and display-ready images. Our sys

Dual Illumination Estimation for Robust Exposure Correction[pdf]AbstractExposure correction is one of the fundamental tasks in image processing and computational photography. While various methods have been proposed, they either fail to produce

本文是第一个对欠曝光和过曝光用同一个网络实现校准的方法。个人认为本文最大的贡献是：1. 本文不是做图像增强，而是曝光错误进行修正。2. 提供了一个全新的、曝光时间范围更广的数据集。

​本博客对曝光校准的相关工作进行简单总结，内容选自 2021CVPR 文章：Learning Multi-Scale Photo Exposure Correction.​

A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement[PAPER]Abstract Self-regularized low-light image enhancement does not require any normal-light image in training, thereby freeing from the chains on paired or unpair.

一种结构和纹理感知 Retinex 模型 (2020 TIP) (1 of 2)STAR: A Structure and Texture Aware Retinex Model[PAPER][GitHub]Fig. 1. An example to illustrate the applications of the proposed STAR model based on Retinex theory. (a) The input low-light and color-disto.

STAR: A Structure and Texture Aware Retinex Model[PAPER][GitHub]Fig. 1. An example to illustrate the applications of the proposed STAR model based on Retinex theory. (a) The input low-light and color-distorted image; (b) the estimated illumination.

Resources for Low Light Image Enhancementhttps://github.com/dawnlh/low-light-image-enhancement-resources-------------------------------------------------------------PaperTIP 2021Sparse Gradient Regularized Deep Retinex Network for Robust Low-Ligh