arrow
返回

Multi-Grid Back-Projection Networks

delete2021-02-01
delete2
delete
OA
AI
P
Pablo Navarrete Michelini *
W
Wenbin Chen
H
Hanwen Liu
D
Dan Zhu
X
Xingqun Jiang
DOI:10.1109/JSTSP.2021.3049641delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Multi-grid back-projection (MGBP) is a fully-convolutional network architecture that can learn to restore images and videos with upscaling artifacts. Using the same strategy of multi-grid partial differential equation (PDE) solvers this multiscale architecture scales computational complexity efficiently with increasing output resolutions. The basic processing block is inspired in the iterative back-projection (IBP) algorithm and constitutes a type of cross-scale residual block with feedback from low resolution references. The architecture performs in par with state-of-the-arts alternatives for regression targets that aim to recover an exact copy of a high resolution image or video from which only a downscale image is known. A perceptual quality target aims to create more realistic outputs by introducing artificial changes that can be different from a high resolution original content as long as they are consistent with the low resolution input. For this target we propose a strategy using noise inputs in different resolution scales to control the amount of artificial details generated in the output. The noise input controls the amount of innovation that the network uses to create artificial realistic details. The effectiveness of this strategy is shown in benchmarks and it is explained as a particular strategy to traverse the perception-distortion plane.
Keyword:
Image resolution
Videos
Standards
Distortion
Training
Technological innovation
Image reconstruction
Multigrid
iterative backprojection
super resolution
convolutional networks
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Journal of Selected Topics in Signal Processing 封面图
IEEE Journal of Selected Topics in Signal Processing
IF:
13.7
论文数:
1.9K
被引数:
1.1W

机构

暂无机构信息
引用论文

引用论文

err分享
err收藏
Making a Completely Blind Image Quality Analyzer制作全盲图像质量分析仪
err2013-03-01
err4.2K
PREAI
errMittal, Anish; Soundararajan, Rajiv; Bovik, Alan C.
err分享
err收藏
err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
err分享
err收藏
The Nb−Zr (Niobium−Zirconium) system
err1982-06-01
err0
PREAI
errJ. P. Abriata; J. C. Bolcich
err分享
err收藏
学者 查看更多内容