Wasserstein Generative Adversarial Network for Depth Completion With Anisotropic Diffusion Depth Enhancement
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nguyen, Tri Minh | - |
dc.contributor.author | Yoo, Myungsik | - |
dc.date.accessioned | 2022-03-11T05:40:12Z | - |
dc.date.available | 2022-03-11T05:40:12Z | - |
dc.date.created | 2022-03-11 | - |
dc.date.issued | 2022-01 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | http://scholarworks.bwise.kr/ssu/handle/2018.sw.ssu/42014 | - |
dc.description.abstract | The objective of depth completion is to generate a dense depth map by upsampling a sparse one. However, irregular sparse patterns or the lack of groundtruth data caused by unstructured data make depth completion extremely challenging. Sensor fusion using both RGB and LIDAR sensors can help produce a more reliable context with higher accuracy. Compared with previous approaches, this method takes semantic segmentation images as additional input and develops an unsupervised loss function. Thus, when combined with supervised depth loss, the depth completion problem is considered as semi-supervised learning. We used an adapted Wasserstein Generative Adversarial Network architecture instead of applying the traditional autoencoder approach and post-processing process to preserve valid depth measurements received from the input and further enhance the depth value precision of the results. Our proposed method was evaluated on the KITTI depth completion benchmark, and its performance in depth completion was proven to be competitive. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.title | Wasserstein Generative Adversarial Network for Depth Completion With Anisotropic Diffusion Depth Enhancement | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3142916 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.10, pp.6867 - 6877 | - |
dc.description.journalClass | 1 | - |
dc.identifier.wosid | 000745489300001 | - |
dc.identifier.scopusid | 2-s2.0-85123309849 | - |
dc.citation.endPage | 6877 | - |
dc.citation.startPage | 6867 | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 10 | - |
dc.contributor.affiliatedAuthor | Yoo, Myungsik | - |
dc.type.docType | Article | - |
dc.description.isOpenAccess | N | - |
dc.subject.keywordAuthor | Generators | - |
dc.subject.keywordAuthor | Laser radar | - |
dc.subject.keywordAuthor | Generative adversarial networks | - |
dc.subject.keywordAuthor | Computer architecture | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Semantics | - |
dc.subject.keywordAuthor | Depth completion | - |
dc.subject.keywordAuthor | LIDAR sparse depth | - |
dc.subject.keywordAuthor | anisotropic diffusion | - |
dc.subject.keywordAuthor | generative adversarial network | - |
dc.subject.keywordAuthor | Wasserstein GAN | - |
dc.subject.keywordPlus | UNSUPERVISED DEPTH | - |
dc.subject.keywordPlus | PREDICTION | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Soongsil University Library 369 Sangdo-Ro, Dongjak-Gu, Seoul, Korea (06978)02-820-0733
COPYRIGHT ⓒ SOONGSIL UNIVERSITY, ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.