Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Qian Ye , Masanori Suganuma , Takayuki Okatani
{"title":"Improved high dynamic range imaging using multi-scale feature flows balanced between task-orientedness and accuracy","authors":"Qian Ye ,&nbsp;Masanori Suganuma ,&nbsp;Takayuki Okatani","doi":"10.1016/j.cviu.2024.104126","DOIUrl":null,"url":null,"abstract":"<div><p>Deep learning has made it possible to accurately generate high dynamic range (HDR) images from multiple images taken at different exposure settings, largely owing to advancements in neural network design. However, generating images without artifacts remains difficult, especially in scenes with moving objects. In such cases, issues like color distortion, geometric misalignment, or ghosting can appear. Current state-of-the-art network designs address this by estimating the optical flow between input images to align them better. The parameters for the flow estimation are learned through the primary goal, producing high-quality HDR images. However, we find that this ”task-oriented flow” approach has its drawbacks, especially in minimizing artifacts. To address this, we introduce a new network design and training method that improve the accuracy of flow estimation. This aims to strike a balance between task-oriented flow and accurate flow. Additionally, the network utilizes multi-scale features extracted from the input images for both flow estimation and HDR image reconstruction. Our experiments demonstrate that these two innovations result in HDR images with fewer artifacts and enhanced quality.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"248 ","pages":"Article 104126"},"PeriodicalIF":4.3000,"publicationDate":"2024-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1077314224002078/pdfft?md5=35e8f40c73b01f0b9afae0db47e39486&pid=1-s2.0-S1077314224002078-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002078","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

Abstract

Deep learning has made it possible to accurately generate high dynamic range (HDR) images from multiple images taken at different exposure settings, largely owing to advancements in neural network design. However, generating images without artifacts remains difficult, especially in scenes with moving objects. In such cases, issues like color distortion, geometric misalignment, or ghosting can appear. Current state-of-the-art network designs address this by estimating the optical flow between input images to align them better. The parameters for the flow estimation are learned through the primary goal, producing high-quality HDR images. However, we find that this ”task-oriented flow” approach has its drawbacks, especially in minimizing artifacts. To address this, we introduce a new network design and training method that improve the accuracy of flow estimation. This aims to strike a balance between task-oriented flow and accurate flow. Additionally, the network utilizes multi-scale features extracted from the input images for both flow estimation and HDR image reconstruction. Our experiments demonstrate that these two innovations result in HDR images with fewer artifacts and enhanced quality.

利用多尺度特征流改进高动态范围成像,兼顾任务导向性和准确性
主要由于神经网络设计的进步,深度学习已经能够从不同曝光设置下拍摄的多幅图像中准确生成高动态范围(HDR)图像。然而,生成没有伪影的图像仍然很困难,尤其是在有移动物体的场景中。在这种情况下,可能会出现色彩失真、几何错位或重影等问题。目前最先进的网络设计通过估计输入图像之间的光流来解决这一问题,从而更好地对齐图像。光流估计的参数是通过生成高质量 HDR 图像这一主要目标来学习的。然而,我们发现这种 "以任务为导向的光流 "方法有其缺点,尤其是在最小化伪影方面。为了解决这个问题,我们引入了一种新的网络设计和训练方法,以提高流量估计的准确性。这样做的目的是在面向任务的流量和精确流量之间取得平衡。此外,该网络还利用从输入图像中提取的多尺度特征进行流量估计和 HDR 图像重建。我们的实验证明,这两项创新所生成的 HDR 图像具有更少的伪影和更高的质量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信