arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1902.01077cs.CV
收藏

跳跃流形:运动中几何感知的稠密非刚性运动恢复结构

Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure from Motion

Australian National University(澳大利亚国立大学)

Suryansh Kumar

摘要:

针对非刚性运动物体在多帧图像中的密集特征对应关系,提出了一种在每帧图像中估计其三维形状的算法。为了准确地解决这个问题,最近的国家的最先进的算法减少了这个任务的局部线性子空间重建和聚类问题,使用格拉斯曼流形表示\cite{kumar2018scalable}。不幸的是,他们的方法错过了与表面变形建模相关的一些关键问题,例如,局部表面变形对其相邻表面的依赖性。此外,它们对高维数据点进行分组的表示不可避免地引入了在高维Grassmann流形\cite{huang2015projection, harandi2014manifold}上对样本进行分类的缺点。因此,为了处理这样的限制与\cite{kumar2018scalable},我们提出了一种算法,联合利用高维格拉斯曼流形的好处来执行重建,其等效的低维表示来推断合适的集群。为了实现这一点,我们将每个格拉斯曼投影到一个低维格拉斯曼流形上,该流形保留并尊重结构相对于其邻居的变形。这些较低维度的格拉斯曼点然后充当用于选择高维格拉斯曼样本以执行每个局部重建的代表。在实践中,我们的算法提供了一种几何上有效的方法来解决密集NRSfM之间切换流形的基础上,它的好处和用途。实验结果表明,该算法在处理噪声方面是非常有效的,重建精度与竞争方法一样好或更好。

英文摘要:

Given dense image feature correspondences of a non-rigidly moving object across multiple frames, this paper proposes an algorithm to estimate its 3D shape for each frame. To solve this problem accurately, the recent state-of-the-art algorithm reduces this task to set of local linear subspace reconstruction and clustering problem using Grassmann manifold representation \cite{kumar2018scalable}. Unfortunately, their method missed on some of the critical issues associated with the modeling of surface deformations, for e.g., the dependence of a local surface deformation on its neighbors. Furthermore, their representation to group high dimensional data points inevitably introduce the drawbacks of categorizing samples on the high-dimensional Grassmann manifold \cite{huang2015projection, harandi2014manifold}. Hence, to deal with such limitations with \cite{kumar2018scalable}, we propose an algorithm that jointly exploits the benefit of high-dimensional Grassmann manifold to perform reconstruction, and its equivalent lower-dimensional representation to infer suitable clusters. To accomplish this, we project each Grassmannians onto a lower-dimensional Grassmann manifold which preserves and respects the deformation of the structure w.r.t its neighbors. These Grassmann points in the lower-dimension then act as a representative for the selection of high-dimensional Grassmann samples to perform each local reconstruction. In practice, our algorithm provides a geometrically efficient way to solve dense NRSfM by switching between manifolds based on its benefit and usage. Experimental results show that the proposed algorithm is very effective in handling noise with reconstruction accuracy as good as or better than the competing methods.

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。

↑