DCVSMNet: Double Cost Volume Stereo Matching Network

Mahmoud Tahmasebi, Saif Huq, Kevin Meehan, Marion McAfee
2/26/2024
cs.CV

No official code found. Best implementation: M2219/DCVSMNet (20 stars, MIT, last commit 2025-06-10).

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 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.

View on arXivView PDF

Code Implementations(1)

M2219/DCVSMNetCommunity100%
MIT

A fast and accurate stereo matching network with powerful generalization on real-world datasets

207PythonFeb 15, 20241 years agoMIT

Similar Papers

LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation

89% match1 repo9412024

Iterative Geometry Encoding Volume for Stereo Matching

88% match1 repo6762026

Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networks

86% match2024

Generalized Geometry Encoding Volume for Real-time Stereo Matching

86% match2025

Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution

85% match1 repo382025

Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching

83% match1 repo82026

Cite this paper

@article{tahmasebi2024dcvsmnet,
  title  = {DCVSMNet: Double Cost Volume Stereo Matching Network},
  author = {Mahmoud Tahmasebi and Saif Huq and Kevin Meehan and Marion McAfee},
  year   = {2024},
  eprint = {2402.16473},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.16473v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.16473.svg)](https://codeofpaper.com/paper/2402.16473)

Discussion