arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09593cs.CV
收藏

基于立体图像的快速层次深度图计算

Fast Hierarchical Depth Map Computation from Stereo

IIT Delhi(德里印度理工学院)

Vinay Kaushik, Brejesh Lall

摘要:

块匹配立体视差通常用于计算能力有限的应用中,以便获得深度估计。然而,对简单立体方法的研究一直少于基于能量的方法,基于能量的方法保证了更好质量的深度图,具有更大的未来改进潜力。半全局匹配(SGM)方法具有良好的性能和易于实现,但由于它是在全视差空间图像上工作,因此存在非常高的内存占用问题。另一方面,块匹配立体需要更少的内存。在本文中,我们介绍了一种新的多尺度层次块匹配方法,使用金字塔的深度和成本函数的变体,大大提高了标准块匹配立体技术的结果,同时保持低内存占用,进一步降低标准块匹配的复杂性。我们测试了我们的新的多块匹配方案的米德尔伯里立体声基准。对于Middlebury基准测试,我们得到的结果只比最先进的SGM实现略差。

英文摘要:

Disparity by Block Matching stereo is usually used in applications with limited computational power in order to get depth estimates. However, the research on simple stereo methods has been lesser than the energy based counterparts which promise a better quality depth map with more potential for future improvements. Semi-global-matching (SGM) methods offer good performance and easy implementation but suffer from the problem of very high memory footprint because it's working on the full disparity space image. On the other hand, Block matching stereo needs much less memory. In this paper, we introduce a novel multi-scale-hierarchical block-matching approach using a pyramidal variant of depth and cost functions which drastically improves the results of standard block matching stereo techniques while preserving the low memory footprint and further reducing the complexity of standard block matching. We tested our new multi block matching scheme on the Middlebury stereo benchmark. For the Middlebury benchmark we get results that are only slightly worse than state of the art SGM implementations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑