I'm a first-year Ph.D. student at the University of Michigan in Computer Science and Engineering, advised by David Fouhey. My primary research interest lies in Computer Vision, espeically 3D vision and recognition.

Within 3D vision, I'm particularly interested in recovering 3D representations from Internet videos and computer graphics.

I obtained my bachelor degree from both the University of Michigan and Shanghai Jiao Tong University. During my undergraduate study at Michigan, I worked with Jia Deng in Vision & Learning Lab.


Learning Single-Image Depth from Videos using Quality Assessment Networks.
Weifeng Chen, Shengyi Qian, Jia Deng.
CVPR 2019.

We propose a method to automatically generate training data for single-view depth through Structure-from-Motion (SfM) on Internet videos.


Instructional Aide / Teaching Assistant:

Course Projects

These projects mainly represent my undergraduate work.

DiagNet: Bridging Text and Image.
Xinyi Zheng, Shengyi Qian, Yi Wen, Mark Jin, Tim Shen.
Course Project, EECS 498/598 Deep Learning, 2019 Winter. Instructor: Prof. Honglak Lee.
Convision: Bring Vision to the Blind through Conversation.
Yi Wen, Chung-Hsun Wang, I-Le Wu, Shengyi Qian, Ray Cao, Linyi Jin, Xinyi Zheng.
Capstone Project, 2019 Winter.
Surface Normal Prediction from a Single Image.
Shengyi Qian, Linyi Jin, Yichen Yang.
Instructor: Jia Deng.
Course Project, EECS 442 Computer Vision, 2018 Winter.
[slides] [code]


  • My GPG public key is available here.
  • During my study at Shanghai Jiao Tong University, I was a member of Dongyue Studio, where I contributed to Tongqu (a popular event platform of SJTU) and the freshman junxun website.
  • My notes when I took MATH 371 (Intro to Numerical Methods) by Selim Esedoglu in 2017 Fall.