Attention Concatenation Volume for Accurate and Efficient Stereo Matching. (arXiv:2203.02146v3 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2203.02146

Stereo matching is a fundamental building block for many vision and robotics
applications. An informative and concise cost volume representation is vital
for stereo matching of high accuracy and efficiency. In this paper, we present
a novel cost volume construction method which generates attention weights from
correlation clues to suppress redundant information and enhance
matching-related information in the concatenation volume. To generate reliable
attention weights, we propose multi-level adaptive patch matching to improve
the distinctiveness of the matching cost at …

arxiv attention cv