SteROI-D combines region-of-interest and temporal sparsity with a heterogeneous accelerator and binned mapping to achieve up to 4.35x lower energy for stereo depth inference than a full-frame baseline ASIC.
MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
SteROI-D: System Design and Mapping for Stereo Depth Inference on Regions of Interest
SteROI-D combines region-of-interest and temporal sparsity with a heterogeneous accelerator and binned mapping to achieve up to 4.35x lower energy for stereo depth inference than a full-frame baseline ASIC.