View : 484 Download: 0
Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation
- Title
- Stereo Confidence Estimation via Locally Adaptive Fusion and Knowledge Distillation
- Authors
- Kim S.; Min D.; Frossard P.; Sohn K.
- Ewha Authors
- 민동보
- SCOPUS Author ID
- 민동보
- Issue Date
- 2023
- Journal Title
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- ISSN
- 0162-8828
- Citation
- IEEE Transactions on Pattern Analysis and Machine Intelligence vol. 45, no. 5, pp. 6372 - 6385
- Keywords
- deep learning; knowledge distillation; stereo confidence estimation; Stereo matching
- Publisher
- IEEE Computer Society
- Indexed
- SCIE; SCOPUS
- Document Type
- Article
- 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.
- DOI
- 10.1109/TPAMI.2022.3207286
- Appears in Collections:
- 인공지능대학 > 컴퓨터공학과 > Journal papers
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML