arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1601.06274cs.CV
收藏

基于离散-连续优化的实时的稠密图像匹配

Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization

Institute for Computer Graphics and Vision, Graz University of Technology(格拉茨工业大学计算机图形与视觉研究所)

Alexander Shekhovtsov, Christian Reinbacher, Gottfried Graber, Thomas Pock

摘要:

稠密图像匹配是计算机视觉中一个基本的底层问题,受到离散和连续优化领域的极大关注。本文的目标是在一个连贯的框架中结合离散和连续优化的优点。我们设计了一个基于能量最小化的模型,通过离散和连续算法以一致的方式进行优化。在离散设置,我们提出了一种新的优化算法,可以大规模并行化。在连续的设置,我们解决的问题,非凸正则化的制定基于凸函数的差异。由此产生的混合离散-连续算法可以有效地加速现代GPU,我们证明了其实时的【形】性能密集立体匹配和光流的应用。

英文摘要:

Dense image matching is a fundamental low-level problem in Computer Vision, which has received tremendous attention from both discrete and continuous optimization communities. The goal of this paper is to combine the advantages of discrete and continuous optimization in a coherent framework. We devise a model based on energy minimization, to be optimized by both discrete and continuous algorithms in a consistent way. In the discrete setting, we propose a novel optimization algorithm that can be massively parallelized. In the continuous setting we tackle the problem of non-convex regularizers by a formulation based on differences of convex functions. The resulting hybrid discrete-continuous algorithm can be efficiently accelerated by modern GPUs and we demonstrate its real-time performance for the applications of dense stereo matching and optical flow.

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。

↑