Jing Wu

Redmond, WA, US, 98052

Hi, I’m Jing Wu, a computer vision engineer in Nvidia. I got my bachelor degree in Physics from Fudan University (FDU), Shanghai. Then I spent two years in the Chinese University of Hong Kong (CUHK), Shatin, Hongkong and Shanghai Jiaotong university (SJTU), Shanghai as a research assitant founding my interest in computer vision. After that I went to Georgia Institute of Technology (Gatech), Atlanta and got my master of science degree in computer science. I also completed a master’s Thesis under the supervision of Professor Frank Dellaert.

My interests mainly focus on Simultaneous Localization and Lapping (SLAM), Structure from Motion (SFM), Computer Vision (CV), and Perception in Robotics. My major language in programming is C++ and Python.

news

Sep 15, 2020	I have my personal website!

selected publications

ECCV

Shonan Rotation Averaging: Global Optimality by Surfing SO(p)^n

Frank, Dellaert, David, Rosen, Jing, Wu, Robert, Mahony, and Luca, Carlone

2020

Abs HTML PDF

Shonan Rotation Averaging is a fast, simple, and elegant rotation averaging algorithm that is guaranteed to recover globally optimal solutions under mild assumptions on the measurement noise. Our method employs semidefinite relaxation in order to recover provably globally optimal solutions of the rotation averaging problem. In contrast to prior work, we show how to solve large-scale instances of these relaxations using manifold minimization on (only slightly) higher-dimensional rotation manifolds, re-using existing high-performance (but local) structure-from-motion pipelines. Our method thus preserves the speed and scalability of current SFM methods, while recovering globally optimal solutions.