DCVSMNet: Double Cost Volume Stereo Matching Network

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.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
• Computing the Stereo Matching Cost with a Convolutional Neural Network
• Hierarchical Neural Architecture Search for Deep Stereo Matching
• CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interaction