BriefGPT.xyz
Dec, 2014
深度卷积网络图像超分辨率
Image Super-Resolution Using Deep Convolutional Networks
HTML
PDF
Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang
TL;DR
本文提出一种深度学习方法用于图像超分辨率，采用卷积神经网络直接将低分辨率图片转换为高分辨率图片，能够实现较快的速度和超强的恢复质量，扩展支持三种颜色通道同时处理。
Abstract
We propose a
deep learning
method for single image
super-resolution
(SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep
→