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 2103.16317cs.CV
收藏

流形上的深度回归:3D旋转案例研究

Deep Regression on Manifolds: A 3D Rotation Case Study

NAVER LABS Europe(NAVER欧洲实验室)

Romain Brégier

摘要:

许多机器学习问题涉及在非欧几里德流形上回归变量-例如离散概率分布或对象的6D姿态。通过基于梯度的学习来解决这些问题的一种方法是使用可微函数,该函数将欧几里得空间的任意输入映射到流形上。在本文中,我们建立了一套理想的性质,这样的映射,特别是突出的重要性,前图像的连接性/凸性。我们说明了这些属性与3D旋转的案例研究。通过各种任务的理论考虑和方法实验,我们回顾了3D旋转空间上的各种可微映射,并推测其局部线性的重要性。我们表明,一个映射的基础上的Procrustes正交归一化一般表现最好的映射考虑,但旋转矢量表示可能也是合适的,当限制到小角度。

英文摘要:

Many machine learning problems involve regressing variables on a non-Euclidean manifold -- e.g. a discrete probability distribution, or the 6D pose of an object. One way to tackle these problems through gradient-based learning is to use a differentiable function that maps arbitrary inputs of a Euclidean space onto the manifold. In this paper, we establish a set of desirable properties for such mapping, and in particular highlight the importance of pre-images connectivity/convexity. We illustrate these properties with a case study regarding 3D rotations. Through theoretical considerations and methodological experiments on a variety of tasks, we review various differentiable mappings on the 3D rotation space, and conjecture about the importance of their local linearity. We show that a mapping based on Procrustes orthonormalization generally performs best among the mappings considered, but that a rotation vector representation might also be suitable when restricted to small angles.

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。

↑