Please use this identifier to cite or link to this item: https://repository.cihe.edu.hk/jspui/handle/cihe/3561
DC FieldValueLanguage
dc.contributor.authorSiu, Wan Chien_US
dc.contributor.authorLiu, Zhisong-
dc.contributor.otherCani, M.-P.-
dc.date.accessioned2022-10-12T10:31:59Z-
dc.date.available2022-10-12T10:31:59Z-
dc.date.issued2022-
dc.identifier.urihttps://repository.cihe.edu.hk/jspui/handle/cihe/3561-
dc.description.abstractWe present See360, which is a versatile and efficient framework for 360° panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360° panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360° panoramic view interpolation.en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartofIEEE Transactions on Image Processingen_US
dc.titleSee360: Novel panoramic view interpolationen_US
dc.typejournal articleen_US
dc.identifier.doi10.1109/TIP.2022.3148819-
dc.contributor.affiliationSchool of Computing and Information Sciencesen_US
dc.relation.issn1941-0042en_US
dc.description.volume31en_US
dc.description.startpage1857en_US
dc.description.endpage1869en_US
dc.cihe.affiliatedYes-
item.grantfulltextopen-
item.cerifentitytypePublications-
item.openairetypejournal article-
item.openairecristypehttp://purl.org/coar/resource_type/c_6501-
item.fulltextWith Fulltext-
item.languageiso639-1en-
crisitem.author.deptSchool of Computing and Information Sciences-
crisitem.author.deptSchool of Computing and Information Sciences-
crisitem.author.orcid0000-0001-8280-0367-
crisitem.author.orcid0000-0003-4507-3097-
Appears in Collections:CIS Publication
Files in This Item:
File Description SizeFormat
View Online89 BHTMLView/Open
SFX Query Show simple item record

Google ScholarTM

Check

Altmetric

Altmetric


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