Optimization Inspired Neural Networks for Multiview 3D

Optimization Inspired Neural Networks for Multiview 3D (via Zoom)

Abstract: Multiview 3D has traditionally been approached as an optimization problem. The solution is produced by an algorithm which searches over continuous variables (camera pose, depth, 3D points) to maximally satisfy both geometric constraints and visual observations. 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 be discussing a hybrid approach to multiview problems, where we show that optimization algorithms can be learned from example. This general approach has led to substantial improvements in accuracy on optical flow, stereo, and visual SLAM.

Bio: Zachary Teed is a 4th year PhD student a Princeton University. He is a member of the Princeton Vision and Learning Lab and advised by Professor Jia Deng. His research focuses on problems in multiview perception including optical flow, stereo, scene flow, and visual SLAM. Previously, Zachary graduated from Washington University in St. Louis with a B.S. in computer science. He has received several awards including the Qualcomm Innovation Fellowship, the Jacobus Fellowship, and the ECCV 2020 Best Paper Award.