File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Book Chapter: Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing

TitleTowards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing
Authors
KeywordsImage demoiréing
Image restoration
Ultra-high-definition
Issue Date24-Oct-2022
PublisherSpringer
Abstract

With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i.e., ultra-high-definition) images. However, for image demoiréing, a challenging task in low-level vision, existing works are generally carried out on low-resolution or synthetic images. Hence, the effectiveness of these methods on 4K resolution images is still unknown. In this paper, we explore moiré pattern removal for ultra-high-definition images. To this end, we propose the first ultra-high-definition demoiréing dataset (UHDM), which contains 5,000 real-world 4K resolution image pairs, and conduct a benchmark study on current state-of-the-art methods. Further, we present an efficient baseline model ESDNet for tackling 4K moiré images, wherein we build a semantic-aligned scale-aware module to address the scale variation of moiré patterns. Extensive experiments manifest the effectiveness of our approach, which outperforms state-of-the-art methods by a large margin while being much more lightweight. Code and dataset are available at https://xinyu-andy.github.io/uhdm-page.


Persistent Identifierhttp://hdl.handle.net/10722/337316
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorYu, Xin-
dc.contributor.authorDai, Peng-
dc.contributor.authorLi, Wenbo-
dc.contributor.authorMa, Lan-
dc.contributor.authorShen, Jiajun-
dc.contributor.authorLi, Jia-
dc.contributor.authorQi, Xiaojuan-
dc.date.accessioned2024-03-11T10:19:50Z-
dc.date.available2024-03-11T10:19:50Z-
dc.date.issued2022-10-24-
dc.identifier.isbn9783031197963-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/337316-
dc.description.abstract<p>With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i.e., ultra-high-definition) images. However, for image demoiréing, a challenging task in low-level vision, existing works are generally carried out on low-resolution or synthetic images. Hence, the effectiveness of these methods on 4K resolution images is still unknown. In this paper, we explore moiré pattern removal for ultra-high-definition images. To this end, we propose the first ultra-high-definition demoiréing dataset (UHDM), which contains 5,000 real-world 4K resolution image pairs, and conduct a benchmark study on current state-of-the-art methods. Further, we present an efficient baseline model ESDNet for tackling 4K moiré images, wherein we build a semantic-aligned scale-aware module to address the scale variation of moiré patterns. Extensive experiments manifest the effectiveness of our approach, which outperforms state-of-the-art methods by a large margin while being much more lightweight. Code and dataset are available at <a href="https://xinyu-andy.github.io/uhdm-page">https://xinyu-andy.github.io/uhdm-page</a>.</p>-
dc.languageeng-
dc.publisherSpringer-
dc.relation.ispartofComputer Vision – ECCV 2022-
dc.subjectImage demoiréing-
dc.subjectImage restoration-
dc.subjectUltra-high-definition-
dc.titleTowards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing-
dc.typeBook_Chapter-
dc.identifier.doi10.1007/978-3-031-19797-0_37-
dc.identifier.scopuseid_2-s2.0-85142697470-
dc.identifier.volume13678 LNCS-
dc.identifier.spage646-
dc.identifier.epage662-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000904379300032-
dc.identifier.eisbn9783031197970-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats