A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch
[article]
2019
arXiv
pre-print
Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference. Towards this goal, we developed a differentiable PatchMatch module that allows us to discard most disparities without requiring full cost volume evaluation. We then exploit this representation to learn which range to prune for each pixel. By progressively reducing the search space and effectively propagating such information, we are able to efficiently compute the cost
arXiv:1909.05845v1
fatcat:qb5kigyqwfbfznyx57fmmbxogq