BriefGPT.xyz
Mar, 2022
用于真实图片降噪的选择性残差M-Net
Selective Residual M-Net for Real Image Denoising
HTML
PDF
Chi-Mao Fan, Tsung-Jung Liu, Kuan-Hsien Liu
TL;DR
本文介绍了一种基于U-Net模型结构并采用选择性核和残差块来实现多尺度语义信息丰富的盲实际图像降噪网络（SRMNet），在两个合成和两个真实噪声数据集上具有竞争性的性能结果。
Abstract
image restoration
is a low-level vision task which is to restore degraded images to noise-free images. With the success of
deep neural networks
, the
→