MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching

TL;DR

MobileStereoNet introduces lightweight 2D and 3D deep models for stereo matching that significantly reduce computational costs while maintaining high accuracy, suitable for deployment on resource-limited devices.

Contribution

The paper proposes two novel lightweight stereo matching models using MobileNet blocks and a new cost volume to balance efficiency and accuracy.

Findings

2D model reduces parameters by 27% and operations by 72%.

3D model reduces parameters by 95% and operations by 38%.

Both models maintain high accuracy comparable to heavier networks.

Abstract

Recent methods in stereo matching have continuously improved the accuracy using deep models. This gain, however, is attained with a high increase in computation cost, such that the network may not fit even on a moderate GPU. This issue raises problems when the model needs to be deployed on resource-limited devices. For this, we propose two light models for stereo vision with reduced complexity and without sacrificing accuracy. Depending on the dimension of cost volume, we design a 2D and a 3D model with encoder-decoders built from 2D and 3D convolutions, respectively. To this end, we leverage 2D MobileNet blocks and extend them to 3D for stereo vision application. Besides, a new cost volume is proposed to boost the accuracy of the 2D model, making it performing close to 3D networks. Experiments show that the proposed 2D/3D networks effectively reduce the computational expense (27%/95% and 72%/38% fewer parameters/operations in 2D and 3D models, respectively) while upholding the accuracy. Our code is available at https://github.com/cogsys-tuebingen/mobilestereonet.