RENOIR 弱光下彩色图像据集

RENOIR 全称 Real Low-Light Image Noise Reduction，是低光照条件下的彩色图像数据集，共包含 120 个场景中的 500 张图像。这些图像由在弱光环境下的三个摄像头采集（Cannon T3i 、 Cannon S90 和小米 MI3 手机）。数据集分有自然噪声图像和低噪声图像，每张图像约为 1 千万像素。

RENOIR, whose full name is Real Low-Light Image Noise Reduction, is a color image dataset dedicated to low-light image noise reduction. It contains 500 images across 120 unique scenes, which were captured by three cameras in low-light environments: Cannon T3i, Cannon S90, and Xiaomi MI3 smartphone. The dataset is divided into naturally noisy images and low-noise images, with each image having approximately 10 million pixels.

搜集汇总

背景与挑战

背景概述

RENOIR是一个低光照条件下的彩色图像数据集，包含120个场景中的500张图像，由三个摄像头在弱光环境下采集，每张约1千万像素，分为自然噪声和低噪声版本。该数据集适用于研究图像噪声形成与统计，以及训练和测试去噪算法。