I'm a third-year Ph.D student of Computer Science and Engineering at the University of Michigan, working with David Fouhey. My primary research interest lies in 3D vision and recognition.

Before that, I obtained my B.S.E. from both the University of Michigan and Shanghai Jiao Tong University, and I worked with Jia Deng in Vision & Learning Lab.

News

  • [2021/07] "Planar Surface Reconstruction from Sparse Views" is accepted at ICCV 2021!
  • [2021/04] I will have an internship at Facebook AI Research with Georgia Gkioxari this summer!
  • [2020/08] Associative3D is invited to present at ECCV 2020 Workshop Holistic Scene Structures for 3D Vision.
  • [2020/07] "Associative3D: Volumetric Reconstruction from Sparse Views" is accepted at ECCV 2020!

Research

Surface Normal
Depth
Voxels
Planes

My research focuses on 3D vision and recognition, i.e. how do we recover the 3D world from one or few 2D images? The wall above demonstrates different 3D representations we extract from 2D images in my recent research projects.

Publications

Planar Surface Reconstruction from Sparse Views.
ICCV 2021 (Oral)

We create a planar reconstruction of a scene from two very distant camera viewpoints.

[project page] [paper] [code] [video]

Associative3D: Volumetric Reconstruction from Sparse Views.
Shengyi Qian*, Linyi Jin*, David Fouhey.
ECCV 2020

We present Associative3D, which addresses 3D volumetric reconstruction from two views of a scene with an unknown camera, by simultaneously reconstructing objects and figuring out their relationship.

[eccv talk] [slides]

Invited presentation at ECCV 2020 Workshop Holistic Scene Structures for 3D Vision.
OASIS: A Large-Scale Dataset for Single-Image 3D in the Wild.
Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng.
CVPR 2020

We present Open Annotations of Single Image Surfaces (OASIS), a dataset for single-image 3D in the wild consisting of dense annotations of detailed 3D geometry for Internet images.

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.

Teaching