3.8 Proceedings Paper

Learning to Optimize Non-Rigid Tracking

出版社

IEEE
DOI: 10.1109/CVPR42600.2020.00496

关键词

-

资金

  1. TUM-IAS Rudolf Mossbauer Fellowship
  2. ERC Starting Grant Scan2CAD [804724]
  3. German Research Foundation (DFG) Grant Making Machine Learning on Static and Dynamic 3D Data Practical
  4. JST CREST [JPMJCR1403]
  5. JSPS KAKENHI [JP19H01115]
  6. Erasmus+ grant

向作者/读者索取更多资源

One of the widespread solutions for non-rigid tracking has a nested-loop structure: with Gauss-Newton to minimize a tracking objective in the outer loop, and Preconditioned Conjugate Gradient (PCG) to solve a sparse linear system in the inner loop. In this paper, we employ learnable optimizations to improve tracking robustness and speed up solver convergence. First, we upgrade the tracking objective by integrating an alignment data term on deep features which are learned end-to-end through CNN. The new tracking objective can capture the global deformation which helps Gauss-Newton to jump over local minimum, leading to robust tracking on large non-rigid motions. Second, we bridge the gap between the preconditioning technique and learning method by introducing a ConditionNet which is trained to generate a preconditioner such that PCG can converge within a small number of steps. Experimental results indicate that the proposed learning method converges faster than the original PCG by a large margin.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据