Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/96492
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Electronic and Information Engineering | - |
dc.creator | Liu, ZS | en_US |
dc.creator | Cani, MP | en_US |
dc.creator | Siu, WC | en_US |
dc.date.accessioned | 2022-12-07T02:55:11Z | - |
dc.date.available | 2022-12-07T02:55:11Z | - |
dc.identifier.issn | 1057-7149 | en_US |
dc.identifier.uri | http://hdl.handle.net/10397/96492 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/ | en_US |
dc.rights | The following publication Liu, Z. S., Cani, M. P., & Siu, W. C. (2022). See360: Novel Panoramic View Interpolation. IEEE Transactions on Image Processing, 31, 1857-1869 is available at https://doi.org/10.1109/TIP.2022.3148819. | en_US |
dc.subject | 3D scene | en_US |
dc.subject | Adversarial network | en_US |
dc.subject | View rendering | en_US |
dc.title | See360 : novel panoramic view interpolation | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 1857 | en_US |
dc.identifier.epage | 1869 | en_US |
dc.identifier.volume | 31 | en_US |
dc.identifier.doi | 10.1109/TIP.2022.3148819 | en_US |
dcterms.abstract | We 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. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE transactions on image processing, 2022, v. 31, p. 1857-1869 | en_US |
dcterms.isPartOf | IEEE transactions on image processing | en_US |
dcterms.issued | 2022 | - |
dc.identifier.scopus | 2-s2.0-85124744557 | - |
dc.identifier.pmid | 35139016 | - |
dc.identifier.eissn | 1941-0042 | en_US |
dc.description.validate | 202212 bckw | - |
dc.description.oa | Version of Record | en_US |
dc.identifier.FolderNumber | OA_Scopus/WOS | - |
dc.description.pubStatus | Published | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
See360_Novel_Panoramic_View_Interpolation.pdf | 4.54 MB | Adobe PDF | View/Open |
Page views
56
Last Week
3
3
Last month
Citations as of May 12, 2024
Downloads
30
Citations as of May 12, 2024
SCOPUSTM
Citations
2
Citations as of May 16, 2024
WEB OF SCIENCETM
Citations
2
Citations as of May 16, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.