Convolutional neural network based deep conditional random fields for stereo matching
详细信息 查看全文
- 作者：Zhi Wang ; 11325067@zju.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Shiqiang Zhu ; Yuehua Li ; Zhengzhe Cui
- 关键词：Stereo matching ; Conditional random fields ; Convolutional neural network
- 刊名：Journal of Visual Communication and Image Representation
- 出版年：2016
- 出版时间：October 2016
- 年：2016
- 卷：40
- 期：part_PB
- 页码：739-750
- 全文大小：3280 K
文摘
- •
A deep CRF based stereo matching algorithm with CNN is proposed.
- •
The CNN potential function learns the potentials of CRF in a CNN framework.
- •
The inference of the deep CRF model is formulated as a Recurrent Neural Network.
- •
The deep CRF based algorithm outperforms other MRF-based or CRF-based methods.