Efficient Deep Learning for Stereo Matching
Citations Over TimeTop 1% of 2016 papers
Abstract
In the past year, convolutional neural networks have been shown to perform extremely well for stereo estimation. However, current architectures rely on siamese networks which exploit concatenation followed by further processing layers, requiring a minute of GPU computation per image pair. In contrast, in this paper we propose a matching network which is able to produce very accurate results in less than a second of GPU computation. Towards this goal, we exploit a product layer which simply computes the inner product between the two representations of a siamese architecture. We train our network by treating the problem as multi-class classification, where the classes are all possible disparities. This allows us to get calibrated scores, which result in much better matching performance when compared to existing approaches.
Related Papers
- → AEG: Automatic Exploit Generation(2018)209 cited
- → PExy: The Other Side of Exploit Kits(2014)24 cited
- → Automated Crash Analysis and Exploit Generation with Extendable Exploit Model(2022)4 cited
- → AEMB: An Automated Exploit Mitigation Bypassing Solution(2021)5 cited
- Korean text-to-speech and concatenation cost function(2006)