For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Asymmetric Learning for Stereo Matching Cost Computation
Zhongjian MA Dongzhen HUANG Baoqing LI Xiaobing YUAN
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2020/10/01
Online ISSN: 1745-1361
Type of Manuscript: PAPER
Category: Artificial Intelligence, Data Mining
stereo matching, asymmetric convolutions, feature extraction, CNN,
Full Text: PDF>>
Current stereo matching methods benefit a lot from the precise stereo estimation with Convolutional Neural Networks (CNNs). Nevertheless, patch-based siamese networks rely on the implicit assumption of constant depth within a window, which does not hold for slanted surfaces. Existing methods for handling slanted patches focus on post-processing. In contrast, we propose a novel module for matching cost networks to overcome this bias. Slanted objects appear horizontally stretched between stereo pairs, suggesting that the feature extraction in the horizontal direction should be different from that in the vertical direction. To tackle this distortion, we utilize asymmetric convolutions in our proposed module. Experimental results show that the proposed module in matching cost networks can achieve higher accuracy with fewer parameters compared to conventional methods.