Randomly Sparsified Synthesis for Model-Based Deformation Analysis
Randomly Sparsified Synthesis for Model-Based Deformation Analysis
复制标题
DOI：
10.1007/978-3-319-45886-1_12
复制
发表时间：
2016-09
期刊：
影响因子：
--
通讯作者：
Stefan Reinhold;Andreas Jordt;R. Koch
中科院分区：
文献类型：
--
作者：
Stefan Reinhold;Andreas Jordt;R. Koch
变形跟踪是计算机视觉当前的挑战之一。基于综合分析 (AbS) 的变形跟踪提供了一种将颜色和深度数据非常自然地融合到单个优化问题中的方法。先前的工作表明，使用稀疏合成可以非常有效地完成此任务。尽管稀疏合成允许基于 AbS 的跟踪实时执行，但它需要大量针对特定问题的定制，并且仅限于某些场景。本文介绍了一种参考模型随机自适应稀疏化的新方法，该方法在优化过程中根据当前优化步骤所需的精度来调整稀疏化。结果表明，使用所提出的方法可以显着提高 AbS 的效率。
The tracking of deformation is one of the current challenges in computer vision. Analysis by Synthesis (AbS) based deformation tracking provides a way to fuse color and depth data into a single optimization problem very naturally. Previous work has shown that this can be done very efficiently using sparse synthesis. Although sparse synthesis allows AbS-based tracking to perform in real-time, it requires a great amount of problem specific customization and is limited to certain scenarios. This article introduces a new way of randomized adaptive sparsification of the reference model that adjusts the sparsification during the optimization process according to the required accuracy of the current optimization step. It will be shown that the efficiency of AbS can be increased significantly using the proposed method.