DCVSMNet: Double Cost Volume Stereo Matching Network

arXiv:2402.16473v1 Announce Type: new
Abstract: 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 …

abstract architecture arxiv correlation cost cs.cv geometry information network norm novel small type wise