用于图像超分辨率的轻量级哈希定向全局感知和自校准多尺度融合网络

IF 4.2 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Image and Vision Computing Pub Date : 2024-09-04 DOI:10.1016/j.imavis.2024.105255
Zhisheng Cui , Yibing Yao , Shilong Li , Yongcan Zhao , Ming Xin
{"title":"用于图像超分辨率的轻量级哈希定向全局感知和自校准多尺度融合网络","authors":"Zhisheng Cui ,&nbsp;Yibing Yao ,&nbsp;Shilong Li ,&nbsp;Yongcan Zhao ,&nbsp;Ming Xin","doi":"10.1016/j.imavis.2024.105255","DOIUrl":null,"url":null,"abstract":"<div><p>In recent years, with the increase in the depth and width of convolutional neural networks, single image super-resolution (SISR) algorithms have made significant breakthroughs in objective quantitative metrics and subjective visual quality. However, these operations have inevitably caused model inference time to surge. In order to find a balance between model speed and accuracy, we propose a lightweight hash-directed global perception and self-calibrated multiscale fusion network for image Super-Resolution (HSNet) in this paper. The HSNet makes the following two main improvements: first, the Hash-Directed Global Perception module (HDGP) designed in this paper is able to capture the dependencies between features in a global perspective by using the hash encoding to direct the attention mechanism. Second, the Self-Calibrated Multiscale Fusion module (SCMF) proposed in this paper has two independent task branches: the upper branch of the SCMF utilizes the feature fusion module to capture multiscale contextual information, while the lower branch focuses on local details through a small convolutional kernel. These two branches are fused with each other to effectively enhance the network's multiscale understanding capability. Extensive experimental results demonstrate the remarkable superiority of our approach over other state-of-the-art methods in both subjective visual effects and objective evaluation metrics, including PSNR, SSIM, and computational complexity.</p></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"151 ","pages":"Article 105255"},"PeriodicalIF":4.2000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A lightweight hash-directed global perception and self-calibrated multiscale fusion network for image super-resolution\",\"authors\":\"Zhisheng Cui ,&nbsp;Yibing Yao ,&nbsp;Shilong Li ,&nbsp;Yongcan Zhao ,&nbsp;Ming Xin\",\"doi\":\"10.1016/j.imavis.2024.105255\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In recent years, with the increase in the depth and width of convolutional neural networks, single image super-resolution (SISR) algorithms have made significant breakthroughs in objective quantitative metrics and subjective visual quality. However, these operations have inevitably caused model inference time to surge. In order to find a balance between model speed and accuracy, we propose a lightweight hash-directed global perception and self-calibrated multiscale fusion network for image Super-Resolution (HSNet) in this paper. The HSNet makes the following two main improvements: first, the Hash-Directed Global Perception module (HDGP) designed in this paper is able to capture the dependencies between features in a global perspective by using the hash encoding to direct the attention mechanism. Second, the Self-Calibrated Multiscale Fusion module (SCMF) proposed in this paper has two independent task branches: the upper branch of the SCMF utilizes the feature fusion module to capture multiscale contextual information, while the lower branch focuses on local details through a small convolutional kernel. These two branches are fused with each other to effectively enhance the network's multiscale understanding capability. Extensive experimental results demonstrate the remarkable superiority of our approach over other state-of-the-art methods in both subjective visual effects and objective evaluation metrics, including PSNR, SSIM, and computational complexity.</p></div>\",\"PeriodicalId\":50374,\"journal\":{\"name\":\"Image and Vision Computing\",\"volume\":\"151 \",\"pages\":\"Article 105255\"},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Image and Vision Computing\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0262885624003603\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Image and Vision Computing","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0262885624003603","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

摘要

近年来,随着卷积神经网络深度和宽度的增加,单图像超分辨率(SISR)算法在客观量化指标和主观视觉质量方面都取得了重大突破。然而,这些操作不可避免地导致模型推理时间激增。为了在模型速度和精度之间找到平衡点,我们在本文中提出了一种轻量级哈希定向全局感知和自校准多尺度融合网络(HSNet)用于图像超分辨率。HSNet 主要做了以下两方面的改进:首先,本文设计的哈希定向全局感知模块(HDGP)能够通过哈希编码引导注意力机制,从全局角度捕捉特征之间的依赖关系。其次,本文提出的自校准多尺度融合模块(SCMF)有两个独立的任务分支:SCMF 的上层分支利用特征融合模块捕捉多尺度上下文信息,下层分支则通过小卷积核关注局部细节。这两个分支相互融合,有效增强了网络的多尺度理解能力。广泛的实验结果表明,我们的方法在主观视觉效果和客观评价指标(包括 PSNR、SSIM 和计算复杂度)方面都明显优于其他最先进的方法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A lightweight hash-directed global perception and self-calibrated multiscale fusion network for image super-resolution

In recent years, with the increase in the depth and width of convolutional neural networks, single image super-resolution (SISR) algorithms have made significant breakthroughs in objective quantitative metrics and subjective visual quality. However, these operations have inevitably caused model inference time to surge. In order to find a balance between model speed and accuracy, we propose a lightweight hash-directed global perception and self-calibrated multiscale fusion network for image Super-Resolution (HSNet) in this paper. The HSNet makes the following two main improvements: first, the Hash-Directed Global Perception module (HDGP) designed in this paper is able to capture the dependencies between features in a global perspective by using the hash encoding to direct the attention mechanism. Second, the Self-Calibrated Multiscale Fusion module (SCMF) proposed in this paper has two independent task branches: the upper branch of the SCMF utilizes the feature fusion module to capture multiscale contextual information, while the lower branch focuses on local details through a small convolutional kernel. These two branches are fused with each other to effectively enhance the network's multiscale understanding capability. Extensive experimental results demonstrate the remarkable superiority of our approach over other state-of-the-art methods in both subjective visual effects and objective evaluation metrics, including PSNR, SSIM, and computational complexity.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Image and Vision Computing
Image and Vision Computing 工程技术-工程:电子与电气
CiteScore
8.50
自引率
8.50%
发文量
143
审稿时长
7.8 months
期刊介绍: Image and Vision Computing has as a primary aim the provision of an effective medium of interchange for the results of high quality theoretical and applied research fundamental to all aspects of image interpretation and computer vision. The journal publishes work that proposes new image interpretation and computer vision methodology or addresses the application of such methods to real world scenes. It seeks to strengthen a deeper understanding in the discipline by encouraging the quantitative comparison and performance evaluation of the proposed methodology. The coverage includes: image interpretation, scene modelling, object recognition and tracking, shape analysis, monitoring and surveillance, active vision and robotic systems, SLAM, biologically-inspired computer vision, motion analysis, stereo vision, document image understanding, character and handwritten text recognition, face and gesture recognition, biometrics, vision-based human-computer interaction, human activity and behavior understanding, data fusion from multiple sensor inputs, image databases.
期刊最新文献
CF-SOLT: Real-time and accurate traffic accident detection using correlation filter-based tracking TransWild: Enhancing 3D interacting hands recovery in the wild with IoU-guided Transformer Machine learning applications in breast cancer prediction using mammography Channel and Spatial Enhancement Network for human parsing Non-negative subspace feature representation for few-shot learning in medical imaging
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1