Patch Loss: A generic multi-scale perceptual loss for single image super-resolution
An T(安泰)1,2; Mao BJ(毛彬杰)1,2; Xue B(薛斌)1,2; Huo CL(霍春雷)1,2; Xiang SM(向世明)1,2; Pan CH(潘春洪)1,2
Source PublicationPattern Recognition
2023-03
Volume139Pages:109510
Abstract

In single image super-resolution (SISR), although PSNR is a key metric for signal fidelity, images with high PSNR do not necessarily render high visual quality. As a result, current perception-driven SISR methods employ perceptual metrics close to the human eye to measure the quality of the generated images. Unfortunately, the perceptual loss and adversarial loss, widely used by the perception-driven SISR methods, still underperform on these non-differentiable perceptual metrics. To this end, we propose a generic multi-scale perceptual loss, i.e., the patch loss, which can be easily plugged into off-the-shelf SISR methods to improve a broad range of perceptual metrics. Specifically, the proposed patch loss minimizes the multi-scale similarity of image patches and enhances the restoration of regions with complex textures and sharp edges via parameter-free adaptive patch-wise attention. Our proposed patch loss introduces more realistic details compared to the perceptual loss and fewer artifacts compared to the adversarial loss.

KeywordSingle-image super-resolution Multi-scale loss functions Image visual perception Perceptual metrics
Indexed BySCI
Language英语
IS Representative Paper
Sub direction classification图像视频处理与分析
planning direction of the national heavy laboratory多尺度信息处理
Paper associated data
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/54534
Collection多模态人工智能系统全国重点实验室_先进时空数据分析与学习
Corresponding AuthorHuo CL(霍春雷)
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
An T,Mao BJ,Xue B,et al. Patch Loss: A generic multi-scale perceptual loss for single image super-resolution[J]. Pattern Recognition,2023,139:109510.
APA An T,Mao BJ,Xue B,Huo CL,Xiang SM,&Pan CH.(2023).Patch Loss: A generic multi-scale perceptual loss for single image super-resolution.Pattern Recognition,139,109510.
MLA An T,et al."Patch Loss: A generic multi-scale perceptual loss for single image super-resolution".Pattern Recognition 139(2023):109510.
Files in This Item: Download All
File Name/Size DocType Version Access License
Patch Loss.pdf(5876KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[An T(安泰)]'s Articles
[Mao BJ(毛彬杰)]'s Articles
[Xue B(薛斌)]'s Articles
Baidu academic
Similar articles in Baidu academic
[An T(安泰)]'s Articles
[Mao BJ(毛彬杰)]'s Articles
[Xue B(薛斌)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[An T(安泰)]'s Articles
[Mao BJ(毛彬杰)]'s Articles
[Xue B(薛斌)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Patch Loss.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.