Timezone: »

 
Poster
An Analysis of SVD for Deep Rotation Estimation
Jake Levinson · Carlos Esteves · Kefan Chen · Noah Snavely · Angjoo Kanazawa · Afshin Rostamizadeh · Ameesh Makadia

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #451
in Poster Session 2 »

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 of SVD as used for projection 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.

Author Information

Jake Levinson (University of Washington)
Carlos Esteves (University of Pennsylvania)
Kefan Chen (Google)
Noah Snavely (Cornell University and Google AI)
Angjoo Kanazawa (UC Berkeley)
Afshin Rostamizadeh (Google Research)
Ameesh Makadia (Google Research)

More from the Same Authors