BriefGPT.xyz
Mar, 2015
从外部和内部示例中共同学习超分辨率
Learning Super-Resolution Jointly from External and Internal Examples
HTML
PDF
Zhangyang Wang, Yingzhen Yang, Zhaowen Wang, Shiyu Chang, Jianchao Yang...
TL;DR
通过稀疏编码外部样本和内部纹理匹配的独特方式，提出了一种联合超分辨率映射模型，进一步通过自适应权重融合，实现了更好的效果。
Abstract
single image super-resolution
(SR) aims to estimate a high-resolution (HR) image from a lowresolution (LR) input.
image priors
are commonly learned to regularize the otherwise seriously ill-posed SR problem, eith
→