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 2006.14616cs.CV
收藏

用于深度旋转估计的SVD分析

An Analysis of SVD for Deep Rotation Estimation

University of Washington(华盛顿大学);University of Pennsylvania(宾夕法尼亚大学);Google Research(谷歌研究院)

Jake Levinson, Carlos Esteves, Kefan Chen, Noah Snavely, Angjoo Kanazawa, Afshin Rostamizadeh, Ameesh Makadia

摘要:

经由SVD的对称正交化以及密切相关的过程是用于将矩阵投影到$O(n)$或$SO(n)$上的公知技术。这些工具长期以来一直用于计算机视觉中的应用,例如通过正交Procrustes、旋转平均或基本矩阵分解解决的最佳3D对准问题。尽管SVD正交化在不同的设置中具有实用性,但在深度学习模型中,SVD正交化作为生成旋转矩阵的过程通常被忽视,其中偏好倾向于经典表示,如单位四元数,欧拉角和轴角,或最近引入的方法。尽管3D旋转在计算机视觉和机器人技术中很重要,但仍然缺少一个通用的有效表示。在这里,我们探讨的可行性SVD正交化的三维旋转神经网络。我们提出了一个理论分析,表明SVD是自然的选择投影到旋转组。我们广泛的定量分析表明,简单地用SVD正交化过程替换现有的表示,在许多涵盖监督和无监督训练的深度学习应用中获得了最先进的性能。

英文摘要:

Symmetric orthogonalization via SVD, and closely related procedures, are well-known techniques for projecting matrices onto $O(n)$ or $SO(n)$. These tools have long been used for applications in computer vision, for example optimal 3D alignment problems solved by orthogonal Procrustes, rotation averaging, or Essential matrix decomposition. Despite its utility in different settings, SVD orthogonalization as a procedure for producing rotation matrices is typically overlooked in deep learning models, where the preferences tend toward classic representations like unit quaternions, Euler angles, and axis-angle, or more recently-introduced methods. Despite the importance of 3D rotations in computer vision and robotics, a single universally effective representation is still missing. Here, we explore the viability of SVD orthogonalization for 3D rotations in neural networks. We present a theoretical analysis that shows SVD is the natural choice for projecting onto the rotation group. Our extensive quantitative analysis shows simply replacing existing representations with the SVD orthogonalization procedure obtains state of the art performance in many deep learning applications covering both supervised and unsupervised training.

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。

↑