AI Seminar sponsored by Fortive

Jia Deng -- Optimization Inspired Deep Architectures for Multiview 3D

Abstract: Multiview 3D has traditionally been approached as continuous optimization: the solution is produced by an algorithm that solves an optimization problem over continuous variables (camera pose, 3D points, motion) to maximize the satisfaction of known constraints from multiview geometry. In contrast, deep learning offers an alternative strategy where the solution is produced by a general-purpose network with learned weights. In this talk, I will present some recent work using a hybrid approach that takes the best of both worlds. In particular, I will present several new deep architectures inspired by classical optimization-based algorithms. These architectures have substantially improved the state of the art of a range of tasks including optical flow, scene flow, and depth estimation. As an aside, I will also discuss how to perform numerically stable backpropagation on 3D transformation groups, needed for end-to-end training of such architectures.

Bio: Jia Deng is an Assistant Professor of Computer Science at Princeton University. His research focus is on computer vision and machine learning. He received his Ph.D. from Princeton University and his B.Eng. from Tsinghua University, both in computer science. He has received a number of awards including the Sloan Research Fellowship, the NSF CAREER award, the ONR Young Investigator award, an ICCV Marr Prize, and two ECCV Best Paper Awards.