Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHong, Yuchenen_US
dc.contributor.authorZheng, Qianen_US
dc.contributor.authorZhao, Lingranen_US
dc.contributor.authorJiang, Xudongen_US
dc.contributor.authorKot, Alex Chichungen_US
dc.contributor.authorShi, Boxinen_US
dc.identifier.citationHong, Y., Zheng, Q., Zhao, L., Jiang, X., Kot, A. C. & Shi, B. (2023). PAR 2Net: end-to-end panoramic image reflection removal. IEEE Transactions On Pattern Analysis and Machine Intelligence, 45(10), 12192-12205.
dc.description.abstractIn this article, we investigate the problem of panoramic image reflection removal to relieve the content ambiguity between the reflection layer and the transmission scene. Although a partial view of the reflection scene is attainable in the panoramic image and provides additional information for reflection removal, it is not trivial to directly apply this for getting rid of undesired reflections due to its misalignment with the reflection-contaminated image. We propose an end-to-end framework to tackle this problem. By resolving misalignment issues with adaptive modules, the high-fidelity recovery of reflection layer and transmission scenes is accomplished. We further propose a new data generation approach that considers the physics-based formation model of mixture images and the in-camera dynamic range clipping to diminish the domain gap between synthetic and real data. Experimental results demonstrate the effectiveness of the proposed method and its applicability for mobile devices and industrial applications.en_US
dc.description.sponsorshipNanyang Technological Universityen_US
dc.relation.ispartofIEEE Transactions on Pattern Analysis and Machine Intelligenceen_US
dc.rights© 2023 IEEE. All rights reserved.en_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titlePAR 2Net: end-to-end panoramic image reflection removalen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.subject.keywordsDeep Learningen_US
dc.subject.keywordsPanoramic Imageen_US
dc.description.acknowledgementThis work was supported in part by the National Key R&D Program of China under Grant 2021ZD0109800, in part by the National Natural Science Foundation of China under Grants 62136001, 62088102, and 61972119, and in part by the Rapid-Rich Object Search (ROSE) Lab of Nanyang Technological University, Singapore.en_US
item.fulltextNo Fulltext-
Appears in Collections:EEE Journal Articles

Citations 50

Updated on Jul 13, 2024

Page view(s)

Updated on Jul 19, 2024

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.