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
this https URL

该研究提出了两种轻量级的立体视觉模型，采用 2D 和 3D 卷积进行编解码。研究表明，这两种模型有效地减少了计算开销，同时保持了准确性。