Joint self-supervised and reference-guided learning for depth inpainting
Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and also large holes. To improve such data, we propose a joint self-supervised and reference-guided learning approach for depth inpainting. For th...
Uloženo v:
| Vydáno v: | Computational visual media (Beijing) Ročník 8; číslo 4; s. 597 - 612 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Beijing
Tsinghua University Press
01.12.2022
Springer Nature B.V |
| Témata: | |
| ISSN: | 2096-0433, 2096-0662 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and also large holes. To improve such data, we propose a joint self-supervised and reference-guided learning approach for depth inpainting. For the self-supervised learning strategy, we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge information. This module alternately learns a convolutional dictionary and sparse coding from a corrupted depth map. Then, both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map, which is effectively smoothed using local contextual information. The reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth values. We thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large holes. In summary, our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent information. Experimental results show that the proposed approach works well for both invalid value restoration and large hole inpainting. |
|---|---|
| AbstractList | Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and also large holes. To improve such data, we propose a joint self-supervised and reference-guided learning approach for depth inpainting. For the self-supervised learning strategy, we introduce an improved spatial convolutional sparse coding module in which total variation regularization is employed to enhance the structural information while preserving edge information. This module alternately learns a convolutional dictionary and sparse coding from a corrupted depth map. Then, both the learned convolutional dictionary and sparse coding are convolved to yield an initial depth map, which is effectively smoothed using local contextual information. The reference-guided learning part is inspired by the fact that adjacent pixels with close colors in the RGB image tend to have similar depth values. We thus construct a hierarchical joint bilateral filter module using the corresponding color image to fill in large holes. In summary, our approach integrates a convolutional sparse coding module to preserve local contextual information and a hierarchical joint bilateral filter module for filling using specific adjacent information. Experimental results show that the proposed approach works well for both invalid value restoration and large hole inpainting. |
| Author | Wu, Heng Zhao, Yifan Fu, Kui Li, Jia Song, Haokun |
| Author_xml | – sequence: 1 givenname: Heng surname: Wu fullname: Wu, Heng organization: State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University – sequence: 2 givenname: Kui surname: Fu fullname: Fu, Kui organization: State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University – sequence: 3 givenname: Yifan surname: Zhao fullname: Zhao, Yifan organization: State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University – sequence: 4 givenname: Haokun surname: Song fullname: Song, Haokun organization: State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University – sequence: 5 givenname: Jia surname: Li fullname: Li, Jia email: jiali@buaa.edu.cn organization: State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University |
| BookMark | eNp9kE1LxDAQhoOs4LruD_BW8BzNR5umR1nUXVnwoueQNpM1UtOatIL7681SRRD0MMwwzDPvzHuKZr7zgNA5JZeUkPIq5pRUBSaMpigqvD9Cc0YqgYkQbPZd55yfoGWMriZMcEloWc3R-r5zfsgitBbHsYfw7iKYTHuTBbAQwDeAd6MzqdmCDt75XWa7kBnoh-fM-V4nPjXP0LHVbYTlV16gp9ubx9Uabx_uNqvrLW64YAM2NSmpNI3WlFOqOYGi1E0ugBNjRQWiolICY1bXVhhWW2kszU1RNZZIWVu-QBfT3j50byPEQb10Y_BJUjEhC8YKSco0RaepJnQxpk9UH9yrDh-KEnXwTE2eqeSZOnim9okpfzGNG_TgOj8E7dp_STaRMan4HYSfm_6GPgEY74P9 |
| CitedBy_id | crossref_primary_10_1038_s41598_025_08323_5 crossref_primary_10_26599_CVM_2025_9450384 |
| Cites_doi | 10.1109/CVPR.2017.28 10.1007/978-3-030-58589-1_1 10.1109/ICCV.2011.6126488 10.1109/ICCV.2017.566 10.1109/CVPR.2019.01273 10.1007/978-3-642-38886-6_52 10.1016/j.imavis.2013.07.006 10.1109/CVPR.2015.7299149 10.1109/TIP.2017.2718183 10.1137/S0036142903422429 10.1109/ICRA.2018.8460184 10.1109/TIP.2015.2409551 10.1007/978-3-642-33715-4_54 10.1109/3DTV.2011.5877202 10.1016/j.patrec.2012.06.003 10.1109/CVPR.2013.57 10.1109/CVPR.2013.149 10.1109/ICCV.2015.212 10.1109/WACV.2017.145 10.1007/s40436-015-0131-4 10.1109/CVPR.2019.00840 10.1109/CVPR.2018.00026 10.1109/TVCG.2020.3003768 10.1109/CVPR.2010.5539957 10.1109/JSTSP.2017.2743683 10.1007/978-3-319-46487-9_38 10.1109/3DV.2018.00017 10.1007/978-3-319-03731-8_38 10.1109/TPAMI.2012.213 10.5244/C.30.125 10.1016/j.icte.2020.05.004 10.1109/3DV.2017.00012 10.1177/1729881421996544 10.1109/ICCV.2013.127 10.1109/ICRA.2019.8793637 10.1007/978-3-030-01270-0_7 10.1109/CRV.2018.00013 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2022 The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: The Author(s) 2022 – notice: The Author(s) 2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | C6C AAYXX CITATION 7SC 8FD ABUWG AFKRA AZQEC BENPR CCPQU DWQXO JQ2 L7M L~C L~D PHGZM PHGZT PIMPY PKEHL PQEST PQQKQ PQUKI PRINS |
| DOI | 10.1007/s41095-021-0259-z |
| DatabaseName | Springer Nature OA Free Journals CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials Local Electronic Collection Information ProQuest Central ProQuest One Community College ProQuest Central ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ProQuest Central Premium ProQuest One Academic ProQuest Publicly Available Content ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China |
| DatabaseTitle | CrossRef Publicly Available Content Database Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest Central China Computer and Information Systems Abstracts Professional ProQuest Central ProQuest One Academic UKI Edition ProQuest Central Korea ProQuest Central (New) ProQuest One Academic Advanced Technologies Database with Aerospace ProQuest One Academic (New) |
| DatabaseTitleList | Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences Computer Science |
| EISSN | 2096-0662 |
| EndPage | 612 |
| ExternalDocumentID | 10_1007_s41095_021_0259_z |
| GroupedDBID | -0I -0Y -SI -S~ 0R~ 5VR 5VS 92M 9D9 9DI AAFWJ AAKKN AAXDM ABEEZ ABFTD ACACY ACGFS ACULB ADINQ ADMLS AFGXO AFKRA AFPKN AFUIB AHBYD AHSBF ALMA_UNASSIGNED_HOLDINGS AMKLP ARCSS BAPOH BENPR C24 C6C CAJEI CCEZO CCPQU CUBFJ EBS EJD FA0 GROUPED_DOAJ IAO ISR ITC JAVBF JUIAU M~E OK1 PIMPY PROAC Q-- Q-8 R-I RSV RT9 S.. SOJ T8Y U1F U1G U5I U5S ~NL AAYXX ABVLG AFFHD CITATION PHGZM PHGZT 7SC 8FD ABUWG AZQEC DWQXO JQ2 L7M L~C L~D PKEHL PQEST PQQKQ PQUKI PRINS |
| ID | FETCH-LOGICAL-c362t-db0718dcaa1311a30e57ac46e30df69e69188e22fabf6d2bf8df14d59cf088bf3 |
| IEDL.DBID | C24 |
| ISICitedReferencesCount | 4 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000801981000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2096-0433 |
| IngestDate | Fri Jul 25 06:38:28 EDT 2025 Wed Nov 12 18:35:32 EST 2025 Tue Nov 18 20:47:34 EST 2025 Fri Feb 21 02:45:29 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | self-supervised learning reference-guided learning depth inpainting |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c362t-db0718dcaa1311a30e57ac46e30df69e69188e22fabf6d2bf8df14d59cf088bf3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| OpenAccessLink | https://link.springer.com/10.1007/s41095-021-0259-z |
| PQID | 2685225807 |
| PQPubID | 4402894 |
| PageCount | 16 |
| ParticipantIDs | proquest_journals_2685225807 crossref_primary_10_1007_s41095_021_0259_z crossref_citationtrail_10_1007_s41095_021_0259_z springer_journals_10_1007_s41095_021_0259_z |
| PublicationCentury | 2000 |
| PublicationDate | 20221200 2022-12-00 20221201 |
| PublicationDateYYYYMMDD | 2022-12-01 |
| PublicationDate_xml | – month: 12 year: 2022 text: 20221200 |
| PublicationDecade | 2020 |
| PublicationPlace | Beijing |
| PublicationPlace_xml | – name: Beijing |
| PublicationTitle | Computational visual media (Beijing) |
| PublicationTitleAbbrev | Comp. Visual Media |
| PublicationYear | 2022 |
| Publisher | Tsinghua University Press Springer Nature B.V |
| Publisher_xml | – name: Tsinghua University Press – name: Springer Nature B.V |
| References | Chen, L.; Lin, H.; Li, S. Depth image enhancement for Kinect using region growing and bilateral filter. In: Proceedings of the 21st International Conference on Pattern Recognition, 3070–3073, 2012. MoriSEratOBrollWSaitoHSchmalstiegDKalkofenDInpaintFusion: Incremental RGB-D inpainting for 3D scenesIEEE Transactions on Visualization and Computer Graphics202026102994300710.1109/TVCG.2020.3003768 GongX JLiuJ YZhouW HLiuJ LGuided depth enhancement via a fast marching methodImage and Vision Computing2013311069570310.1016/j.imavis.2013.07.006 ZhangCWangTImage inpainting using double discriminator generative adversarial networksJournal of Physics: Conference Series202117321012052 Bristow, H.; Eriksson, A.; Lucey, S. Fast convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 391–398, 2013. LiaoMLuFZhouDZhangSLiWYangRVedaldiABischofHBroxTFrahmJ MDVI: Depth guided video inpainting for autonomous drivingComputer Vision — ECCV 20202020ChamSpringer11710.1007/978-3-030-58589-1_1 Liu, J.; Gong, X.; Liu, J. Guided inpainting and filtering for Kinect depth maps. In: Proceedings of the 21st International Conference on Pattern Recognition, 2055–2058, 2012. Zhang, Y. D.; Funkhouser, T. Deep depth completion of a single RGB-D image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 175–185, 2018. Zeiler, M. D.; Krishnan, D.; Taylor, G. W.; Fergus, R. Deconvolutional networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2528–2535, 2010. BarronJ TPooleBLeibeBMatasJSebeNWellingMThe fast bilateral solverComputer Vision — ECCV 20162016ChamSpringer61763210.1007/978-3-319-46487-9_38 Bristow, H.; Lucey, S. Optimization methods for convolutional sparse coding. arXiv preprint arXiv: 1406.2407, 2014. Neven, D.; De Brabandere, B.; Georgoulis, S.; Proesmans, M.; Van Gool, L. Fast scene understanding for autonomous driving. arXiv preprint arXiv:1708. 02550, 2017. KimJHyeonJDohNGenerative multiview inpainting for object removal in large indoor spacesInternational Journal of Advanced Robotic Systems202118217298814219965410.1177/1729881421996544 Jaritz, M.; de Charette, R.; Wirbel, E.; Perrotton, X.; Nashashibi, F. Sparse and dense data with CNNs: Depth completion and semantic segmentation. In: Proceedings of the International Conference on 3D Vision, 52–60, 2018. SilbermanNHoiemDKohliPFergusRFitzgibbonALazebnikSPeronaPSatoYSchmidCIndoor segmentation and support inference from RGBD imagesComputer Vision — ECCV 20122012Berlin HeidelbergSpringer74676010.1007/978-3-642-33715-4_54 Imran, S.; Long, Y.; Liu, X.; Morris, D. Depth coefficients for depth completion. arXiv preprint arXiv:1903.05421, 2019. WangXOngS KNeeA Y CA comprehensive survey of augmented reality assembly researchAdvances in Manufacturing20164112210.1007/s40436-015-0131-4 Hornácek, M.; Rhemann, C.; Gelautz, M.; Rother, C. Depth super resolution by rigid body self-similarity in 3D. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1123–1130, 2013. Hawe, S.; Kleinsteuber, M.; Diepold, K. Dense disparity maps from sparse disparity measurements. In: Proceedings of the International Conference on Computer Vision, 2126–2133, 2011. QiFHanJ YWangP JShiG MLiFStructure guided fusion for depth map inpaintingPattern Recognition Letters2013341707610.1016/j.patrec.2012.06.003 Ferstl, D.; Reinbacher, C.; Ranftl, R.; Ruether, M.; Bischof, H. Image guided depth upsampling using anisotropic total generalized variation. In: Proceedings of the IEEE International Conference on Computer Vision, 993–1000, 2013. Uhrig, J.; Schneider, N.; Schneider, L.; Franke, U.; Brox, T.; Geiger, A. Sparsity invariant CNNs. In: Proceedings of the International Conference on 3D Vision, 11–20, 2017. Zisselman, E.; Sulam, J.; Elad, M. A local block coordinate descent algorithm for the CSC model. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8200–8209, 2019. Tölgyessy, M.; Hubinsky, P. The Kinect sensor in robotics education. In: Proceedings of the 2nd International Conference on Robotics in Education, 143–146, 2011. YangL LLiCHanJ GChenCYeQ XZhangB CCaoXLiuWImage reconstruction via manifold constrained convolutional sparse coding for image setsIEEE Journal of Selected Topics in Signal Processing20171171072108110.1109/JSTSP.2017.2743683 LiuJGongXHuetBNgoC WTangJZhouZ HHauptmannA GYanSGuided depth enhancement via anisotropic diffusionAdvances in Multimedia Information Processing — PCM 20132013ChamSpringer40841710.1007/978-3-319-03731-8_38 LiuLChanS HNguyenT QDepth reconstruction from sparse samples: Representation, algorithm, and samplingIEEE Transactions on Image Processing201524619831996334234010.1109/TIP.2015.2409551 Affara, L.; Ghanem, B.; Wonka, P. Supervised convolutional sparse coding. arXiv preprint arXiv: 1804.02678, 2018. Ku, J.; Harakeh, A.; Waslander, S. L. In defense of classical image processing: Fast depth completion on the CPU. In: Proceedings of the 15th Conference on Computer and Robot Vision, 16–22, 2018. Zhang, H.; Patel, V. M. Convolutional sparse and low-rank coding-based rain streak removal. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259–1267, 2017. Gu, S. H.; Zuo, W. M.; Xie, Q.; Meng, D. Y.; Feng, X. C.; Zhang, L. Convolutional sparse coding for image super-resolution. In: Proceedings of the IEEE International Conference on Computer Vision, 1823–1831, 2015. SteidlGWeickertJBroxTMrázekPWelkMOn the equivalence of soft wavelet shrinkage, total variation diffusion, total variation regularization, and SIDEsSIAM Journal on Numerical Analysis2004422686713208423210.1137/S0036142903422429 Matyunin, S.; Vatolin, D.; Berdnikov, Y.; Smirnov, M. Temporal filtering for depth maps generated by Kinect depth camera. In: Proceedings of the 3DTV Conference: The True Vision — Capture, Transmission and Display of 3D Video, 1–4, 2011. Zhang, H.; Patel, V. Convolutional sparse coding-based image decomposition. In: Proceedings of the British Machine Vision Conference, 125.1–125.11, 2016. HerreraC DKannalaJLadickýLHeikkiläJKämäräinenJ KKoskelaMDepth map inpainting under a second-order smoothness priorImage Analysis2013Berlin HeidelbergSpringer55556610.1007/978-3-642-38886-6_52 HeK MSunJTangX OGuided image filteringIEEE Transactions on Pattern Analysis and Machine Intelligence20133561397140910.1109/TPAMI.2012.213 ChengXWangPYangRFerrariVHebertMSminchisescuCWeissYDepth estimation via affinity learned with convolutional spatial propagation networkComputer Vision — ECCV 20182018ChamSpringer10812510.1007/978-3-030-01270-0_7 Papyan, V.; Romano, Y.; Elad, M.; Sulam, J. Convolutional dictionary learning via local processing. In: Proceedings of the IEEE International Conference on Computer Vision, 5306–5314, 2017. Ma, F. C.; Cavalheiro, G. V.; Karaman, S. Self-supervised sparse-to-dense: Self-supervised depth completion from LiDAR and monocular camera. In: Proceedings of the International Conference on Robotics and Automation, 3288–3295, 2019. Song, S. R.; Yu, F.; Zeng, A.; Chang, A. X.; Savva, M.; Funkhouser, T. Semantic scene completion from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 190–198, 2017. Ma, F. C.; Karaman, S. Sparse-to-dense: Depth prediction from sparse depth samples and a single image. In: Proceedings of the IEEE International Conference on Robotics and Automation, 4796–4803, 2018. KeaomaneeYHeednacramAYoungkongPImplementation of four kriging models for depth inpaintingICT Express20206320921310.1016/j.icte.2020.05.004 XueH YZhangS MCaiDDepth image inpainting: Improving low rank matrix completion with low gradient regularizationIEEE Transactions on Image Processing201726943114320367054610.1109/TIP.2017.2718183 Heide, F.; Heidrich, W.; Wetzstein, G. Fast and flexible convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5135–5143, 2015. X Wang (259_CR2) 2016; 4 259_CR7 259_CR6 259_CR5 259_CR4 259_CR3 J Kim (259_CR11) 2021; 18 259_CR1 J T Barron (259_CR16) 2016 L Liu (259_CR26) 2015; 24 259_CR32 259_CR31 M Liao (259_CR8) 2020 H Y Xue (259_CR18) 2017; 26 L L Yang (259_CR36) 2017; 11 259_CR14 259_CR35 259_CR34 259_CR33 259_CR17 259_CR39 X J Gong (259_CR13) 2013; 31 259_CR38 259_CR37 Y Keaomanee (259_CR19) 2020; 6 X Cheng (259_CR30) 2018 C Zhang (259_CR10) 2021; 1732 J Liu (259_CR15) 2013 K M He (259_CR44) 2013; 35 S Mori (259_CR9) 2020; 26 F Qi (259_CR23) 2013; 34 N Silberman (259_CR43) 2012 G Steidl (259_CR42) 2004; 42 259_CR21 259_CR20 259_CR41 C D Herrera (259_CR12) 2013 259_CR40 259_CR25 259_CR24 259_CR22 259_CR29 259_CR28 259_CR27 |
| References_xml | – reference: Zhang, Y. D.; Funkhouser, T. Deep depth completion of a single RGB-D image. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 175–185, 2018. – reference: XueH YZhangS MCaiDDepth image inpainting: Improving low rank matrix completion with low gradient regularizationIEEE Transactions on Image Processing201726943114320367054610.1109/TIP.2017.2718183 – reference: Ma, F. C.; Karaman, S. Sparse-to-dense: Depth prediction from sparse depth samples and a single image. In: Proceedings of the IEEE International Conference on Robotics and Automation, 4796–4803, 2018. – reference: Affara, L.; Ghanem, B.; Wonka, P. Supervised convolutional sparse coding. arXiv preprint arXiv: 1804.02678, 2018. – reference: KimJHyeonJDohNGenerative multiview inpainting for object removal in large indoor spacesInternational Journal of Advanced Robotic Systems202118217298814219965410.1177/1729881421996544 – reference: Imran, S.; Long, Y.; Liu, X.; Morris, D. Depth coefficients for depth completion. arXiv preprint arXiv:1903.05421, 2019. – reference: Jaritz, M.; de Charette, R.; Wirbel, E.; Perrotton, X.; Nashashibi, F. Sparse and dense data with CNNs: Depth completion and semantic segmentation. In: Proceedings of the International Conference on 3D Vision, 52–60, 2018. – reference: Ku, J.; Harakeh, A.; Waslander, S. L. In defense of classical image processing: Fast depth completion on the CPU. In: Proceedings of the 15th Conference on Computer and Robot Vision, 16–22, 2018. – reference: ZhangCWangTImage inpainting using double discriminator generative adversarial networksJournal of Physics: Conference Series202117321012052 – reference: Liu, J.; Gong, X.; Liu, J. Guided inpainting and filtering for Kinect depth maps. In: Proceedings of the 21st International Conference on Pattern Recognition, 2055–2058, 2012. – reference: LiaoMLuFZhouDZhangSLiWYangRVedaldiABischofHBroxTFrahmJ MDVI: Depth guided video inpainting for autonomous drivingComputer Vision — ECCV 20202020ChamSpringer11710.1007/978-3-030-58589-1_1 – reference: KeaomaneeYHeednacramAYoungkongPImplementation of four kriging models for depth inpaintingICT Express20206320921310.1016/j.icte.2020.05.004 – reference: HeK MSunJTangX OGuided image filteringIEEE Transactions on Pattern Analysis and Machine Intelligence20133561397140910.1109/TPAMI.2012.213 – reference: Tölgyessy, M.; Hubinsky, P. The Kinect sensor in robotics education. In: Proceedings of the 2nd International Conference on Robotics in Education, 143–146, 2011. – reference: MoriSEratOBrollWSaitoHSchmalstiegDKalkofenDInpaintFusion: Incremental RGB-D inpainting for 3D scenesIEEE Transactions on Visualization and Computer Graphics202026102994300710.1109/TVCG.2020.3003768 – reference: Bristow, H.; Eriksson, A.; Lucey, S. Fast convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 391–398, 2013. – reference: Zhang, H.; Patel, V. M. Convolutional sparse and low-rank coding-based rain streak removal. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 1259–1267, 2017. – reference: YangL LLiCHanJ GChenCYeQ XZhangB CCaoXLiuWImage reconstruction via manifold constrained convolutional sparse coding for image setsIEEE Journal of Selected Topics in Signal Processing20171171072108110.1109/JSTSP.2017.2743683 – reference: SteidlGWeickertJBroxTMrázekPWelkMOn the equivalence of soft wavelet shrinkage, total variation diffusion, total variation regularization, and SIDEsSIAM Journal on Numerical Analysis2004422686713208423210.1137/S0036142903422429 – reference: LiuJGongXHuetBNgoC WTangJZhouZ HHauptmannA GYanSGuided depth enhancement via anisotropic diffusionAdvances in Multimedia Information Processing — PCM 20132013ChamSpringer40841710.1007/978-3-319-03731-8_38 – reference: Ferstl, D.; Reinbacher, C.; Ranftl, R.; Ruether, M.; Bischof, H. Image guided depth upsampling using anisotropic total generalized variation. In: Proceedings of the IEEE International Conference on Computer Vision, 993–1000, 2013. – reference: Matyunin, S.; Vatolin, D.; Berdnikov, Y.; Smirnov, M. Temporal filtering for depth maps generated by Kinect depth camera. In: Proceedings of the 3DTV Conference: The True Vision — Capture, Transmission and Display of 3D Video, 1–4, 2011. – reference: Ma, F. C.; Cavalheiro, G. V.; Karaman, S. Self-supervised sparse-to-dense: Self-supervised depth completion from LiDAR and monocular camera. In: Proceedings of the International Conference on Robotics and Automation, 3288–3295, 2019. – reference: Gu, S. H.; Zuo, W. M.; Xie, Q.; Meng, D. Y.; Feng, X. C.; Zhang, L. Convolutional sparse coding for image super-resolution. In: Proceedings of the IEEE International Conference on Computer Vision, 1823–1831, 2015. – reference: HerreraC DKannalaJLadickýLHeikkiläJKämäräinenJ KKoskelaMDepth map inpainting under a second-order smoothness priorImage Analysis2013Berlin HeidelbergSpringer55556610.1007/978-3-642-38886-6_52 – reference: SilbermanNHoiemDKohliPFergusRFitzgibbonALazebnikSPeronaPSatoYSchmidCIndoor segmentation and support inference from RGBD imagesComputer Vision — ECCV 20122012Berlin HeidelbergSpringer74676010.1007/978-3-642-33715-4_54 – reference: WangXOngS KNeeA Y CA comprehensive survey of augmented reality assembly researchAdvances in Manufacturing20164112210.1007/s40436-015-0131-4 – reference: Heide, F.; Heidrich, W.; Wetzstein, G. Fast and flexible convolutional sparse coding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5135–5143, 2015. – reference: Uhrig, J.; Schneider, N.; Schneider, L.; Franke, U.; Brox, T.; Geiger, A. Sparsity invariant CNNs. In: Proceedings of the International Conference on 3D Vision, 11–20, 2017. – reference: Neven, D.; De Brabandere, B.; Georgoulis, S.; Proesmans, M.; Van Gool, L. Fast scene understanding for autonomous driving. arXiv preprint arXiv:1708. 02550, 2017. – reference: Zeiler, M. D.; Krishnan, D.; Taylor, G. W.; Fergus, R. Deconvolutional networks. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2528–2535, 2010. – reference: Bristow, H.; Lucey, S. Optimization methods for convolutional sparse coding. arXiv preprint arXiv: 1406.2407, 2014. – reference: Chen, L.; Lin, H.; Li, S. Depth image enhancement for Kinect using region growing and bilateral filter. In: Proceedings of the 21st International Conference on Pattern Recognition, 3070–3073, 2012. – reference: Song, S. R.; Yu, F.; Zeng, A.; Chang, A. X.; Savva, M.; Funkhouser, T. Semantic scene completion from a single depth image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 190–198, 2017. – reference: ChengXWangPYangRFerrariVHebertMSminchisescuCWeissYDepth estimation via affinity learned with convolutional spatial propagation networkComputer Vision — ECCV 20182018ChamSpringer10812510.1007/978-3-030-01270-0_7 – reference: Hornácek, M.; Rhemann, C.; Gelautz, M.; Rother, C. Depth super resolution by rigid body self-similarity in 3D. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1123–1130, 2013. – reference: Hawe, S.; Kleinsteuber, M.; Diepold, K. Dense disparity maps from sparse disparity measurements. In: Proceedings of the International Conference on Computer Vision, 2126–2133, 2011. – reference: LiuLChanS HNguyenT QDepth reconstruction from sparse samples: Representation, algorithm, and samplingIEEE Transactions on Image Processing201524619831996334234010.1109/TIP.2015.2409551 – reference: Zhang, H.; Patel, V. Convolutional sparse coding-based image decomposition. In: Proceedings of the British Machine Vision Conference, 125.1–125.11, 2016. – reference: BarronJ TPooleBLeibeBMatasJSebeNWellingMThe fast bilateral solverComputer Vision — ECCV 20162016ChamSpringer61763210.1007/978-3-319-46487-9_38 – reference: QiFHanJ YWangP JShiG MLiFStructure guided fusion for depth map inpaintingPattern Recognition Letters2013341707610.1016/j.patrec.2012.06.003 – reference: GongX JLiuJ YZhouW HLiuJ LGuided depth enhancement via a fast marching methodImage and Vision Computing2013311069570310.1016/j.imavis.2013.07.006 – reference: Zisselman, E.; Sulam, J.; Elad, M. A local block coordinate descent algorithm for the CSC model. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8200–8209, 2019. – reference: Papyan, V.; Romano, Y.; Elad, M.; Sulam, J. Convolutional dictionary learning via local processing. In: Proceedings of the IEEE International Conference on Computer Vision, 5306–5314, 2017. – ident: 259_CR1 doi: 10.1109/CVPR.2017.28 – start-page: 1 volume-title: Computer Vision — ECCV 2020 year: 2020 ident: 259_CR8 doi: 10.1007/978-3-030-58589-1_1 – ident: 259_CR25 doi: 10.1109/ICCV.2011.6126488 – ident: 259_CR39 doi: 10.1109/ICCV.2017.566 – ident: 259_CR6 doi: 10.1109/CVPR.2019.01273 – start-page: 555 volume-title: Image Analysis year: 2013 ident: 259_CR12 doi: 10.1007/978-3-642-38886-6_52 – volume: 31 start-page: 695 issue: 10 year: 2013 ident: 259_CR13 publication-title: Image and Vision Computing doi: 10.1016/j.imavis.2013.07.006 – ident: 259_CR22 – ident: 259_CR20 doi: 10.1109/CVPR.2015.7299149 – volume: 26 start-page: 4311 issue: 9 year: 2017 ident: 259_CR18 publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2017.2718183 – volume: 42 start-page: 686 issue: 2 year: 2004 ident: 259_CR42 publication-title: SIAM Journal on Numerical Analysis doi: 10.1137/S0036142903422429 – ident: 259_CR7 doi: 10.1109/ICRA.2018.8460184 – ident: 259_CR4 – volume: 24 start-page: 1983 issue: 6 year: 2015 ident: 259_CR26 publication-title: IEEE Transactions on Image Processing doi: 10.1109/TIP.2015.2409551 – start-page: 746 volume-title: Computer Vision — ECCV 2012 year: 2012 ident: 259_CR43 doi: 10.1007/978-3-642-33715-4_54 – ident: 259_CR24 doi: 10.1109/3DTV.2011.5877202 – volume: 34 start-page: 70 issue: 1 year: 2013 ident: 259_CR23 publication-title: Pattern Recognition Letters doi: 10.1016/j.patrec.2012.06.003 – ident: 259_CR34 doi: 10.1109/CVPR.2013.57 – volume: 1732 start-page: 012052 issue: 1 year: 2021 ident: 259_CR10 publication-title: Journal of Physics: Conference Series – ident: 259_CR21 doi: 10.1109/CVPR.2013.149 – ident: 259_CR37 doi: 10.1109/ICCV.2015.212 – ident: 259_CR35 doi: 10.1109/WACV.2017.145 – volume: 4 start-page: 1 issue: 1 year: 2016 ident: 259_CR2 publication-title: Advances in Manufacturing doi: 10.1007/s40436-015-0131-4 – ident: 259_CR14 – ident: 259_CR40 doi: 10.1109/CVPR.2019.00840 – ident: 259_CR5 doi: 10.1109/CVPR.2018.00026 – volume: 26 start-page: 2994 issue: 10 year: 2020 ident: 259_CR9 publication-title: IEEE Transactions on Visualization and Computer Graphics doi: 10.1109/TVCG.2020.3003768 – ident: 259_CR32 doi: 10.1109/CVPR.2010.5539957 – volume: 11 start-page: 1072 issue: 7 year: 2017 ident: 259_CR36 publication-title: IEEE Journal of Selected Topics in Signal Processing doi: 10.1109/JSTSP.2017.2743683 – start-page: 617 volume-title: Computer Vision — ECCV 2016 year: 2016 ident: 259_CR16 doi: 10.1007/978-3-319-46487-9_38 – ident: 259_CR29 doi: 10.1109/3DV.2018.00017 – start-page: 408 volume-title: Advances in Multimedia Information Processing — PCM 2013 year: 2013 ident: 259_CR15 doi: 10.1007/978-3-319-03731-8_38 – volume: 35 start-page: 1397 issue: 6 year: 2013 ident: 259_CR44 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/TPAMI.2012.213 – ident: 259_CR41 doi: 10.5244/C.30.125 – ident: 259_CR3 – volume: 6 start-page: 209 issue: 3 year: 2020 ident: 259_CR19 publication-title: ICT Express doi: 10.1016/j.icte.2020.05.004 – ident: 259_CR27 doi: 10.1109/3DV.2017.00012 – volume: 18 start-page: 172988142199654 issue: 2 year: 2021 ident: 259_CR11 publication-title: International Journal of Advanced Robotic Systems doi: 10.1177/1729881421996544 – ident: 259_CR17 doi: 10.1109/ICCV.2013.127 – ident: 259_CR28 doi: 10.1109/ICRA.2019.8793637 – start-page: 108 volume-title: Computer Vision — ECCV 2018 year: 2018 ident: 259_CR30 doi: 10.1007/978-3-030-01270-0_7 – ident: 259_CR31 doi: 10.1109/CRV.2018.00013 – ident: 259_CR33 doi: 10.1109/CVPR.2013.57 – ident: 259_CR38 |
| SSID | ssib026380179 ssib051367588 ssj0001920416 ssib043749047 ssib038075566 ssib039590095 ssib044084544 |
| Score | 2.23051 |
| Snippet | Depth information can benefit various computer vision tasks on both images and videos. However, depth maps may suffer from invalid values in many pixels, and... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 597 |
| SubjectTerms | Artificial Intelligence Coding Color imagery Computer Graphics Computer Science Computer vision Dictionaries Image Processing and Computer Vision Modules Pixels Regularization Research Article Supervised learning User Interfaces and Human Computer Interaction |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T-QwELZ4FTTH8RIL3CkFFcjC8SNrVwgQCCG0QggkuijxA4JW2RzJUvDrGWedDZx0NNcmjgvPZOazx_N9CB1QriHpSoIFgCHMhTJYCU0xZJbYZYQ561p2_ZvhaCQfH9VtOHCrw7XKLia2gdpMtD8jP6aJBKggJBmeVH-wV43y1dUgobGIlj1TGfj58tnF6Pau8ygK3kXivg7l2dXFJwDDlBfN7DtTORty9akO5eWYuegToPAEZyIQfL3M8BHhrb4qJf42L2esK536_jwek7YBGnbssM3A71-TX49o_yrCtrntcu1_V-Un-hFQbXQ6c8N1tGDLDbQWEG4U4ke9ia6uJ0XZRLUdO1xPKx-nahiQlSaa653gp2lh4GHQs3iKAFZHxlbNc1SUVVa00hZb6OHy4v78CgctB6whRTbY5IBlpNFZ5vl9MkasGGaaJ5YR4xJlExVLaSl1We4SQ3MnjYu5EUo7iIO5Y9toqZyUdgdFOoYg4yh4FOymbO6UscxRajVgE2qkHSDSLXKqA9G519sYp3OK5tYuKdgl9XZJ3wfocP5JNWP5-G7wfmeLNPzwddobYoCOOmv2r_852e73k-2hVer7Ldr7M_toqXmd2l9oRb81Rf36O3j7B52l-7A priority: 102 providerName: ProQuest |
| Title | Joint self-supervised and reference-guided learning for depth inpainting |
| URI | https://link.springer.com/article/10.1007/s41095-021-0259-z https://www.proquest.com/docview/2685225807 |
| Volume | 8 |
| WOSCitedRecordID | wos000801981000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2096-0662 dateEnd: 20241231 omitProxy: false ssIdentifier: ssj0001920416 issn: 2096-0433 databaseCode: DOA dateStart: 20150101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2096-0662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001920416 issn: 2096-0433 databaseCode: M~E dateStart: 20150101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2096-0662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001920416 issn: 2096-0433 databaseCode: BENPR dateStart: 20150301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2096-0662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001920416 issn: 2096-0433 databaseCode: PIMPY dateStart: 20150301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVAVX databaseName: Springer Nature OA Free Journals customDbUrl: eissn: 2096-0662 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001920416 issn: 2096-0433 databaseCode: C24 dateStart: 20150301 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB5By4EL5SkWyioHTiBLjh9Z-wjVVgXR1QqBVE5R4kdJVaWrJsuhh_72jr3OpiBAgksOdhxFE3vmc8bzfQCvmTAYdBUlEsEQEVJboqVhBCNL7ivKvfORXf_TbLFQJyd6meq4u-G0-5CSjJ56W-wmchqriXH7i5idXN2FXZkrHc7xHYyU4wwnFM3H1FMgVJe3MAvXQSdzLEYVfCb0rdRTUGAWcox5MnCaycTpdbaBRFRESVVGwwFewfmQLf3dW_4c70YQ-0veNYazw73_MsRDeJDQa_ZuM90ewR3XPoa9hGSz5Cc6bBrEIoa2J3D08aJp-6xz555061VwUR2OqVqbbaVOyOm6sdiYpCxOM0TUmXWr_nvWtKuqiaoWT-Hr4fzLwRFJMg7EYHTsia0RxihrqipQ-1ScOjmrjCgcp9YX2hU6V8ox5qvaF5bVXlmfCyu18egCa8-fwU570brnkJkc_YtnOJlwI-Vqr63jnjFnEJYwq9wE6GDs0iSO8yC1cV5u2Zmj8Uo0XhmMV15N4M12yGpD8PG3m_eHL1imtd6VrFAIYiXOswm8Hb7Y2P3Hh734p7tfwn0WKi_iSZp92Okv1-4V3DM_-qa7nMLu-_li-Xkal8I0_ljA6_H1HHuWH46X324AiKL7rA |
| linkProvider | Springer Nature |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Nb9QwEB2VLRK9UD7VhQI-wAVk4Th2Nj4gVBWqXbpd7aFI5RQSf5SgKhuaLIj-KH4j42yyKUj01gOHXBLHUjTPM88ZzzyA51xoDLoxoxLJEBVSGaqk5hQjS-BSFjrrmu7609FsFp-cqPkG_OpqYfyxys4nNo7aLLT_R_6aRzFSBRmz0dvyG_WqUT672klorGBxaH_-wC1b9WbyDu37gvOD98f7Y9qqClCNzrqmJsOoGhudpr7TTBoyK0epFpENmXGRspEK4thy7tLMRYZnLjYuEEYq7XBFZi7EeW_ApvBgH8DmfHI0_9QhmCOaWdDnvXw3d3mJMIXKi3T2lbAiHAl1Ke_l5Z-F7AOu9A3VZNtQ7OuKjzHR6Lly5k8PizDsUrW-HlAErCm4DvCSil78GWx7Bv1X0reJpQfb_5sV7sDtlrWTvdUyuwsbtrgH2y2DJ61_rO7D-MMiL2pS2TNHq2Xp_XCFA9LCkLWeCz1d5gZvtnodpwS3DcTYsv5C8qJM80a64wF8vJbveQiDYlHYHSA6QCfqOK4Y3C3azCljQ8e51ci9uIntEFhn1ES3jdy9nshZsm5B3eAgQRwkHgfJxRBerl8pV11Mrhq829k-aR1alfSGH8KrDj39439O9ujqyZ7BrfHx0TSZTmaHj2GL-9qS5qzQLgzq86V9Ajf19zqvzp-2K43A5-uG1W8Y_FtY |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB2VbYW4lEJbsS20OfREZeH4Ixsfqy0r2qIVBypxixJ_QCoUIpLlwK9nnHU2FFGkiqtjR9F4MvOs8bwH8IUJjUk3pUQiGCJCKkOU1IxgZoldTrmzrmPXP57M5-nZmToJOqdNf9u9L0kuexo8S1PVHtTGHawa30RMu85iPAojfie3a_DSF6S8i08H-nGGzkXjoQzlydXlPfzCldfMHBpTBZ8Ida8M5dWYhRzyn_T8ZjLwe_1ZwiMqOnlVRv1lXsF5Xzl97Cv_zn0DoH1Qg-1S22zz2UZ5A68Dqo2-Ld1wC17Yahs2A8KNQvxocKgXkejH3sLRz6uyaqPGXjrSLGofuhpck1cmWkmgkPNFaXAwSFycR4i0I2Pr9iIqqzovO7WLd_B7dng6PSJB3oFozJotMQXCm9ToPPeUPzmnVk5yLRLLqXGJsomK09Qy5vLCJYYVLjUuFkYq7TA0Fo6_h1F1VdkdiHSMcccxdDI8YNnCKWO5Y8xqhCvMpHYMtDd8pgP3uZfguMxWrM2d8TI0XuaNl92OYX-1pF4Sfzw1ebffzSzEgCZjSYrgVqLPjeFrv3vD43--7MN_zf4M6yffZ9nxj_mvj7DBfHNGd9lmF0bt9cLuwSt905bN9afuz7gDLEACEg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Joint+self-supervised+and+reference-guided+learning+for+depth+inpainting&rft.jtitle=Computational+visual+media+%28Beijing%29&rft.au=Wu%2C+Heng&rft.au=Fu%2C+Kui&rft.au=Zhao%2C+Yifan&rft.au=Song%2C+Haokun&rft.date=2022-12-01&rft.pub=Tsinghua+University+Press&rft.issn=2096-0433&rft.eissn=2096-0662&rft.volume=8&rft.issue=4&rft.spage=597&rft.epage=612&rft_id=info:doi/10.1007%2Fs41095-021-0259-z&rft.externalDocID=10_1007_s41095_021_0259_z |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2096-0433&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2096-0433&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2096-0433&client=summon |