Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 민동보 | * |
dc.date.accessioned | 2023-08-03T16:31:07Z | - |
dc.date.available | 2023-08-03T16:31:07Z | - |
dc.date.issued | 2023 | * |
dc.identifier.issn | 0162-8828 | * |
dc.identifier.other | OAK-33381 | * |
dc.identifier.uri | https://dspace.ewha.ac.kr/handle/2015.oak/265502 | - |
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. © 1979-2012 IEEE. | * |
dc.language | English | * |
dc.publisher | IEEE Computer Society | * |
dc.subject | deep learning | * |
dc.subject | knowledge distillation | * |
dc.subject | stereo confidence estimation | * |
dc.subject | Stereo matching | * |
dc.title | Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation | * |
dc.type | Article | * |
dc.relation.issue | 5 | * |
dc.relation.volume | 45 | * |
dc.relation.index | SCIE | * |
dc.relation.index | SCOPUS | * |
dc.relation.startpage | 6372 | * |
dc.relation.lastpage | 6385 | * |
dc.relation.journaltitle | IEEE Transactions on Pattern Analysis and Machine Intelligence | * |
dc.identifier.doi | 10.1109/TPAMI.2022.3207286 | * |
dc.identifier.wosid | WOS:000964792800066 | * |
dc.identifier.scopusid | 2-s2.0-85139453361 | * |
dc.author.google | Kim S. | * |
dc.author.google | Min D. | * |
dc.author.google | Frossard P. | * |
dc.author.google | Sohn K. | * |
dc.contributor.scopusid | 민동보(7201669172) | * |
dc.date.modifydate | 20240322133757 | * |