We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost volumes. Each cost volume is processed separately, and a coupling module is proposed to fuse the geometry information extracted from the upper and lower cost volumes. DCVSMNet is a fast stereo matching network with a 67 ms inference time and strong generalization ability which can produce competitive results compared to state-of-the-art methods. The results on several bench mark datasets show that DCVSMNet achieves better accuracy than methods such as CGI-Stereo and BGNet at the cost of greater inference time.
@article{arxiv.2402.16473,
title = {DCVSMNet: Double Cost Volume Stereo Matching Network},
author = {Mahmoud Tahmasebi and Saif Huq and Kevin Meehan and Marion McAfee},
journal= {arXiv preprint arXiv:2402.16473},
year = {2024}
}