I am currently a third year Ph.D. student at UC San Diego, advised by Manmohan Chandraker. Before that, I received my bachelor degree from Tsinghua University in 2016, under the supervision of Jiansheng Chen. I have also been fortunate enough to work with Ravi Ramamoorthi, Kalyan Sunkavalli and Olga Veksler. My CV can be found here. My google citation link can be found here. My email address is zhl378[@]eng[.]ucsd[.]edu.

My research interests are mainly in computer vision and computer graphics. Currently I am focusing on using deep learning method to solve inverse rendering problem with complex materials.

Selected Publications

Learning to Reconstruct Shape and Spatially-Varying Reflectance from a Single Image

Zhengqin Li, Zexiang Xu, Ravi Ramamoorthi, Kalyan Sunkavalli and Manmohan Chandraker

SIGGRAPH ASIA, 2018

[paper][video][supplementary material][code (Coming soon)]

Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image

Zhengqin Li, Kalyan Sunkavalli and Manmohan Chandraker

ECCV, 2018 (Oral presentation)

[paper][video][supplementary material]

Learning to See through Turbulent Water

Zhengqin Li*, Zak Murez*, David Kriegman, Ravi Ramamoorthi and Manmohan Chandraker (*Equal contribution)

WACV, 2018

[paper][code and data]

Robust Energy Minimization for BRDF-Invariant Shape from Light Fields

Double Expansion for Multilabel Segmentation with Shape Prior

Lena Gorelick, Zhengqin Li and Olga Veksler

BMVC, 2017 (Oral presentation)

[paper][supplementary material]

Automatic Image Cropping

Jiansheng Chen, Gaocheng Bai, Shaoheng Liang and Zhengqin Li

CVPR, 2016

[paper]

Superpixel Segmentation Using Linear Spectral Clustering

Zhengqin Li and Jiansheng Chen

CVPR, 2015

(Algorithm has been included in OpenCV 3)

[paper][code]

Technical Reports

A Report on Double Expansion: Definition, Algorithm and Properties

Zhengqin Li and Olga Veksler, 2016

(Part of the theoretical results have been included in BMVC, 2017)

[paper]

Geopolycut: Mesh Segmentation via Double Expansion and Geodesic Curvature Minimization

Zhengqin Li and Olga Veksler, 2015

[paper]

Undergraduate Thesis

Weakly-supervised DCNN based joint semantic segmentation

Zhengqin Li and Jiansheng Chen

Outstanding undergraduate thesis award of Tsinghua University

[paper]

Honor and Awards

2016: Powell Fellowship, UC San Diego

2016: Outstanding undergraduate thesis award, Tsinghua University