DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Sunok | ko |
dc.contributor.author | Kim, Seungryong | ko |
dc.contributor.author | Min, Dongbo | ko |
dc.contributor.author | Frossard, Pascal | ko |
dc.contributor.author | Sohn, Kwanghoon | ko |
dc.date.accessioned | 2024-08-16T02:00:09Z | - |
dc.date.available | 2024-08-16T02:00:09Z | - |
dc.date.created | 2024-08-16 | - |
dc.date.issued | 2023-05 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.45, no.5, pp.6372 - 6385 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/322309 | - |
dc.description.abstract | Stereo confidence estimation aims to estimate the reliability of the estimated disparity by stereo matching. Different from the previous methods that exploit the limited input modality, we present a novel method that estimates confidence map of an initial disparity by making full use of tri-modal input, including matching cost, disparity, and color image through deep networks. The proposed network, termed as Locally Adaptive Fusion Networks (LAF-Net), learns locally-varying attention and scale maps to fuse the tri-modal confidence features. Moreover, we propose a knowledge distillation framework to learn more compact confidence estimation networks as student networks. By transferring the knowledge from LAF-Net as teacher networks, the student networks that solely take as input a disparity can achieve comparable performance. To transfer more informative knowledge, we also propose a module to learn the locally-varying temperature in a softmax function. We further extend this framework to a multiview scenario. Experimental results show that LAF-Net and its variations outperform the state-of-the-art stereo confidence methods on various benchmarks. | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation | - |
dc.type | Article | - |
dc.identifier.wosid | 000964792800066 | - |
dc.identifier.scopusid | 2-s2.0-85139453361 | - |
dc.type.rims | ART | - |
dc.citation.volume | 45 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 6372 | - |
dc.citation.endingpage | 6385 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.identifier.doi | 10.1109/TPAMI.2022.3207286 | - |
dc.contributor.localauthor | Kim, Seungryong | - |
dc.contributor.nonIdAuthor | Kim, Sunok | - |
dc.contributor.nonIdAuthor | Min, Dongbo | - |
dc.contributor.nonIdAuthor | Frossard, Pascal | - |
dc.contributor.nonIdAuthor | Sohn, Kwanghoon | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Costs | - |
dc.subject.keywordAuthor | Estimation | - |
dc.subject.keywordAuthor | Color | - |
dc.subject.keywordAuthor | Knowledge engineering | - |
dc.subject.keywordAuthor | Training | - |
dc.subject.keywordAuthor | Image color analysis | - |
dc.subject.keywordAuthor | Stereo matching | - |
dc.subject.keywordAuthor | stereo confidence estimation | - |
dc.subject.keywordAuthor | knowledge distillation | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordPlus | AGGREGATION | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.