File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TIP.2020.2995061
- Scopus: eid_2-s2.0-85088092749
- WOS: WOS:000546910100002
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Fast and Accurate Tensor Completion With Total Variation Regularized Tensor Trains
Title | Fast and Accurate Tensor Completion With Total Variation Regularized Tensor Trains |
---|---|
Authors | |
Keywords | Tensor completion tensor-train decomposition total variation image restoration |
Issue Date | 2020 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83 |
Citation | IEEE Transactions on Image Processing, 2020, v. 29, p. 6918-6931 How to Cite? |
Abstract | We propose a new tensor completion method based on tensor trains. The to-be-completed tensor is modeled as a low-rank tensor train, where we use the known tensor entries and their coordinates to update the tensor train. A novel tensor train initialization procedure is proposed specifically for image and video completion, which is demonstrated to ensure fast convergence of the completion algorithm. The tensor train framework is also shown to easily accommodate Total Variation and Tikhonov regularization due to their low-rank tensor train representations. Image and video inpainting experiments verify the superiority of the proposed scheme in terms of both speed and scalability, where a speedup of up to 155× is observed compared to state-of-the-art tensor completion methods at a similar accuracy. Moreover, we demonstrate the proposed scheme is especially advantageous over existing algorithms when only tiny portions (say, 1%) of the to-be-completed images/videos are known. |
Persistent Identifier | http://hdl.handle.net/10722/289120 |
ISSN | 2023 Impact Factor: 10.8 2023 SCImago Journal Rankings: 3.556 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | KO, CY | - |
dc.contributor.author | Batselier, K | - |
dc.contributor.author | Daniel, L | - |
dc.contributor.author | Yu, W | - |
dc.contributor.author | Wong, N | - |
dc.date.accessioned | 2020-10-22T08:08:06Z | - |
dc.date.available | 2020-10-22T08:08:06Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | IEEE Transactions on Image Processing, 2020, v. 29, p. 6918-6931 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | http://hdl.handle.net/10722/289120 | - |
dc.description.abstract | We propose a new tensor completion method based on tensor trains. The to-be-completed tensor is modeled as a low-rank tensor train, where we use the known tensor entries and their coordinates to update the tensor train. A novel tensor train initialization procedure is proposed specifically for image and video completion, which is demonstrated to ensure fast convergence of the completion algorithm. The tensor train framework is also shown to easily accommodate Total Variation and Tikhonov regularization due to their low-rank tensor train representations. Image and video inpainting experiments verify the superiority of the proposed scheme in terms of both speed and scalability, where a speedup of up to 155× is observed compared to state-of-the-art tensor completion methods at a similar accuracy. Moreover, we demonstrate the proposed scheme is especially advantageous over existing algorithms when only tiny portions (say, 1%) of the to-be-completed images/videos are known. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83 | - |
dc.relation.ispartof | IEEE Transactions on Image Processing | - |
dc.rights | IEEE Transactions on Image Processing. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Tensor completion | - |
dc.subject | tensor-train decomposition | - |
dc.subject | total variation | - |
dc.subject | image restoration | - |
dc.title | Fast and Accurate Tensor Completion With Total Variation Regularized Tensor Trains | - |
dc.type | Article | - |
dc.identifier.email | Wong, N: nwong@eee.hku.hk | - |
dc.identifier.authority | Wong, N=rp00190 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TIP.2020.2995061 | - |
dc.identifier.scopus | eid_2-s2.0-85088092749 | - |
dc.identifier.hkuros | 315881 | - |
dc.identifier.volume | 29 | - |
dc.identifier.spage | 6918 | - |
dc.identifier.epage | 6931 | - |
dc.identifier.isi | WOS:000546910100002 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1057-7149 | - |