About Me

I am a second-year CSE Ph.D. student at the University of Michigan, advised by Prof. David Fouhey. I was previously a Master student in Robotics. Before that, I received my B.S.E. degrees in Computer Science at UM and Mechanical Engineering at Shanghai Jiao Tong University through a dual degree program at UM-SJTU Joint Institute.

I was honored to collaborate with Prof. Andrew Owens during my master's studies; and with Prof. Dmitry Berenson during my undergraduate studies.

[Github] [CV] [Google Scholar]

News

- [2023/03] Perspective Fields for Single Image Camera Calibration is selected as a highlight!
- [2023/02] Two papers are accepted at CVPR 2023!
- [2022/12] We release our latest work on single image camera calibration!
- [2022/07] "PlaneFormers: From Sparse View Planes to 3D Reconstruction" is accepted at ECCV 2022!
- [2022/06] I passed Prelim.

Publication

Linyi Jin, Jianming Zhang, Yannick Hold-Geoffroy, Oliver Wang, Kevin Matzen, Matthew Sticha, David Fouhey,
Perspective Fields for Single Image Camera Calibration.
CVPR 2023 (Highlight -- 2.5% accept rate)
[Project Page] [Paper (arXiv)] [Bibtex]

Nilesh Kulkarni, Linyi Jin, Justin Johnson, David Fouhey,
Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data.
CVPR 2023

Samir Agarwala, Linyi Jin, Chris Rockwell, David Fouhey
PlaneFormers: From Sparse View Planes to 3D Reconstruction.
ECCV 2022
[Project Page] [Paper] [Bibtex]

Shengyi Qian, Linyi Jin, Chris Rockwell, Siyi Chen, David Fouhey
Understanding 3D Object Articulation in Internet Videos.
CVPR 2022
[Project Page] [Paper] [Bibtex]

Linyi Jin, Shengyi Qian, Andrew Owens, David Fouhey
Planar Surface Reconstruction from Sparse Views
ICCV 2021 (Oral)
[Project Page] [Paper] [Code] [ICCV Talk] [Poster] [Slides] [Bibtex]

Shengyi Qian*, Linyi Jin*, David Fouhey
Associative3D: Volumetric Reconstruction from Sparse Views
European Conference on Computer Vision
ECCV 2020
[Project Page] [Paper] [Code] [ECCV Talk] [Slides] [Bibtex]
Invited presentation at ECCV 2020 Workshop Holistic Scene Structures for 3D Vision.

Andrew Price*, Linyi Jin*, Dmitry Berenson
Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter
International Symposium on Robotics Research
ISRR 2019
[arXiv] [Project Page] [Bibtex]