Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid
University of Cambridge, United Kingdom
Computer Vision – ECCV 2010, Lecture Notes in Computer Science, 2010, Volume 6313/2010, 510-523
@article{richardt2010real,
title={Real-time Spatiotemporal Stereo Matching Using the Dual-Cross-Bilateral Grid},
author={Richardt, C. and Orr, D. and Davies, I. and Criminisi, A. and Dodgson, N.},
journal={Computer Vision–ECCV 2010},
pages={510–523},
year={2010},
publisher={Springer}
}
We introduce a real-time stereo matching technique based on a reformulation of Yoon and Kweon’s adaptive support weights algorithm [1]. Our implementation uses the bilateral grid to achieve a speedup of 200x compared to a straightforward full-kernel GPU implementation, making it the fastest technique on the Middlebury website. We introduce a colour component into our greyscale approach to recover precision and increase discriminability. Using our implementation, we speed up spatial-depth superresolution 100x. We further present a spatiotemporal stereo matching approach based on our technique that incorporates temporal evidence in real time (> 14 fps). Our technique visibly reduces flickering and outperforms per-frame approaches in the presence of image noise. We have created five synthetic stereo videos, with ground truth disparity maps, to quantitatively evaluate depth estimation from stereo video. Source code and datasets are available on our project website.
February 7, 2011 by hgpu
