DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bello, Juan Luis Gonzalez | ko |
dc.contributor.author | Kim, Munchurl | ko |
dc.date.accessioned | 2022-11-28T07:00:32Z | - |
dc.date.available | 2022-11-28T07:00:32Z | - |
dc.date.created | 2022-11-28 | - |
dc.date.created | 2022-11-28 | - |
dc.date.issued | 2022-12 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.44, no.12, pp.9131 - 9149 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/301138 | - |
dc.description.abstract | We propose a novel two-stage training strategy with ambiguity boosting for the self-supervised learning of single view depths from stereo images. Our proposed two-stage learning strategy first aims to obtain a coarse depth prior by training an auto-encoder network for a stereoscopic view synthesis task. This prior knowledge is then boosted and used to self-supervise the model in the second stage of training in our novel ambiguity boosting loss. Our ambiguity boosting loss is a confidence-guided type of data augmentation loss that improves the accuracy and consistency of generated depth maps under several transformations of the single-image input. To show the benefits of the proposed two-stage training strategy with boosting, our two previous depth estimation (DE) networks, one with t-shaped adaptive kernels and the other with exponential disparity volumes, are extended with our new learning strategy, referred to as DBoosterNet-t and DBoosterNet-e, respectively. Our self-supervised DBoosterNets are competitive, and in some cases even better, compared to the most recent supervised SOTA methods, and are remarkably superior to the previous self-supervised methods for monocular DE on the challenging KITTI dataset. We present intensive experimental results, showing the efficacy of our method for the self-supervised monocular DE task. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Self-Supervised Deep Monocular Depth Estimation With Ambiguity Boosting | - |
dc.type | Article | - |
dc.identifier.wosid | 000880661400042 | - |
dc.identifier.scopusid | 2-s2.0-85141893139 | - |
dc.type.rims | ART | - |
dc.citation.volume | 44 | - |
dc.citation.issue | 12 | - |
dc.citation.beginningpage | 9131 | - |
dc.citation.endingpage | 9149 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.identifier.doi | 10.1109/TPAMI.2021.3124079 | - |
dc.contributor.localauthor | Kim, Munchurl | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Boosting | - |
dc.subject.keywordAuthor | Cameras | - |
dc.subject.keywordAuthor | Estimation | - |
dc.subject.keywordAuthor | Kernel | - |
dc.subject.keywordAuthor | Task analysis | - |
dc.subject.keywordAuthor | Image reconstruction | - |
dc.subject.keywordAuthor | Monocular depth estimation | - |
dc.subject.keywordAuthor | self-supervised learning | - |
dc.subject.keywordAuthor | ambiguity boosting | - |
dc.subject.keywordPlus | STEREO | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.