Deep learning

Physics

Pure mathematics

Dimension (graph theory)

Mathematics

Operating system

Algorithm

Statistics

Computer engineering

Encoder

Leverage (statistics)

Artificial intelligence

Matching (statistics)

Set (abstract data type)

Programming language

Volume (thermodynamics)

Code (set theory)

Computer science

Computation

Quantum mechanics

3d model

Computer vision

Stereopsis

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. Code: https://github.com/cogsys-tuebingen/mobilestereonet.

MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching