DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Seungryong | ko |
dc.contributor.author | Min, Dongbo | ko |
dc.contributor.author | Ham, Bumsub | ko |
dc.contributor.author | Do, Minh N. | ko |
dc.contributor.author | Sohn, Kwanghoon | ko |
dc.date.accessioned | 2024-08-16T03:00:11Z | - |
dc.date.available | 2024-08-16T03:00:11Z | - |
dc.date.created | 2024-08-16 | - |
dc.date.issued | 2017-09 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.39, no.9, pp.1712 - 1729 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/322326 | - |
dc.description.abstract | Establishing dense correspondences between multiple images is a fundamental task in many applications. However, finding a reliable correspondence between multi-modal or multi-spectral images still remains unsolved due to their challenging photometric and geometric variations. In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate dense multi-modal and multi-spectral correspondences. Based on an observation that self-similarity existing within images is robust to imaging modality variations, we define the descriptor with a series of an adaptive self-correlation similarity measure between patches sampled by a randomized receptive field pooling, in which a sampling pattern is obtained using a discriminative learning. The computational redundancy of dense descriptors is dramatically reduced by applying fast edge-aware filtering. Furthermore, in order to address geometric variations including scale and rotation, we propose a geometry-invariant DASC (GI-DASC) descriptor that effectively leverages the DASC through a superpixel-based representation. For a quantitative evaluation of the GI-DASC, we build a novel multi-modal benchmark as varying photometric and geometric conditions. Experimental results demonstrate the outstanding performance of the DASC and GI-DASC in many cases of dense multi-modal and multi-spectral correspondences. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | DASC: Robust Dense Descriptor for Multi-Modal and Multi-Spectral Correspondence Estimation | - |
dc.type | Article | - |
dc.identifier.wosid | 000406840800002 | - |
dc.identifier.scopusid | 2-s2.0-85029365917 | - |
dc.type.rims | ART | - |
dc.citation.volume | 39 | - |
dc.citation.issue | 9 | - |
dc.citation.beginningpage | 1712 | - |
dc.citation.endingpage | 1729 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.identifier.doi | 10.1109/TPAMI.2016.2615619 | - |
dc.contributor.localauthor | Kim, Seungryong | - |
dc.contributor.nonIdAuthor | Min, Dongbo | - |
dc.contributor.nonIdAuthor | Ham, Bumsub | - |
dc.contributor.nonIdAuthor | Do, Minh N. | - |
dc.contributor.nonIdAuthor | Sohn, Kwanghoon | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Dense correspondence | - |
dc.subject.keywordAuthor | descriptor | - |
dc.subject.keywordAuthor | multi-spectral | - |
dc.subject.keywordAuthor | multi-modal | - |
dc.subject.keywordAuthor | edge-aware filtering | - |
dc.subject.keywordPlus | REGISTRATION | - |
dc.subject.keywordPlus | IMAGES | - |
dc.subject.keywordPlus | SIFT | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.