High-Resolution Stereo Matching based on Sampled Photoconsistency Computation
High-Resolution Stereo Matching based on Sampled Photoconsistency Computation
复制标题
DOI：
10.5244/c.31.41
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
Chloe LeGendre;Konstantinos Batsos;Philippos Mordohai
中科院分区：
文献类型：
--
作者：
Chloe LeGendre;Konstantinos Batsos;Philippos Mordohai
我们提出了一种双目立体的方法，避免在每个像素上进行详尽的光一致性计算，因为它们是冗余的并且计算成本很高，特别是对于高分辨率图像。我们认为，开发可扩展的立体算法是至关重要的，因为图像分辨率预计将继续快速增加。我们的方法依赖于将图像过度分割成超像素，然后对每个超像素的随机像素子集进行光一致性计算。这产生了用于拟合平面的稀疏重构点。平面假设在相邻的超像素之间传播，并通过选择随机的像素子集来对每个超像素进行评估，并在其上聚合竞争平面的光一致性得分。我们进行了大量的测试，以表征该算法在2014年Middlebury基准的全分辨率立体对上的准确性和速度，该基准包含高达600万像素的图像。我们的结果表明，可以在很小的精度损失的情况下实现非常大的计算节省。我们方法1的多线程实现比其他达到类似精度的方法要快，因此它提供了一个有用的精度-速度权衡。
We propose an approach to binocular stereo that avoids exhaustive photoconsistency computations at every pixel, since they are redundant and computationally expensive, especially for high resolution images. We argue that developing scalable stereo algorithms is critical as image resolution is expected to continue increasing rapidly. Our approach relies on oversegmentation of the images into superpixels, followed by photoconsistency computation for only a random subset of the pixels of each superpixel. This generates sparse reconstructed points which are used to fit planes. Plane hypotheses are propagated among neighboring superpixels, and they are evaluated at each superpixel by selecting a random subset of pixels on which to aggregate photoconsistency scores for the competing planes. We performed extensive tests to characterize the performance of this algorithm in terms of accuracy and speed on the full-resolution stereo pairs of the 2014 Middlebury benchmark that contains up to 6-megapixel images. Our results show that very large computational savings can be achieved at a small loss of accuracy. A multi-threaded implementation of our method 1 is faster than other methods that achieve similar accuracy and thus it provides a useful accuracy-speed tradeoff.