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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 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.