|
|
|
|
| LEADER |
01000naa a22002652 4500 |
| 001 |
NLM346292999 |
| 003 |
DE-627 |
| 005 |
20231226031059.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TPAMI.2022.3207286
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1154.xml
|
| 035 |
|
|
|a (DE-627)NLM346292999
|
| 035 |
|
|
|a (NLM)36112555
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Kim, Sunok
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Completed 10.04.2023
|
| 500 |
|
|
|a Date Revised 11.04.2023
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a 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
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Kim, Seungryong
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Min, Dongbo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Frossard, Pascal
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Sohn, Kwanghoon
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on pattern analysis and machine intelligence
|d 1979
|g 45(2023), 5 vom: 16. Mai, Seite 6372-6385
|w (DE-627)NLM098212257
|x 1939-3539
|7 nnns
|
| 773 |
1 |
8 |
|g volume:45
|g year:2023
|g number:5
|g day:16
|g month:05
|g pages:6372-6385
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TPAMI.2022.3207286
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 45
|j 2023
|e 5
|b 16
|c 05
|h 6372-6385
|