Publications

“*” indicates equal contribution

(2019). End-to-End Wireframe Parsing. Tech Report, arXiv:1905.03246 [cs.CV].

Preprint PDF Code Dataset Project

(2018). Learning to Reconstruct 3D Manhattan Wireframes from a Single Image. Tech Report, arXiv:1905.07482 [cs.CV].

Preprint PDF Video

(2018). QuadriFlow: A Scalable and Robust Method for Quadrangulation. Best Paper in SGP 2018.

PDF Code Dataset Project Demo Online Tool

(2017). BandNet: A Neural Network-Based, Multi-Instrument Beatles-Style MIDI Music Composition Machine. Tech Report, arXiv:1812.07126 [cs.SD].

Preprint PDF Audio

(2016). Parallel Computational Protein Design. Methods in Molecular Biology.

PDF Code

(2015). Massively Parallel A* Search on a GPU. Oral presentation in AAAI 2015.

PDF Code Slides Appendix

(2014). An Efficient Parallel Algorithm for Accelerating Computational Protein Design. ISMB 2014, Bioinformatics.

PDF Code Dataset Poster Slides

Recent Posts

Vanishing points are an important concept in 3D vision. Many papers related to them are using a notation called Gaussian sphere …

Awards

Experience

 
 
 
 
 
May 2019 – August 2019
Palo Alto, California

Research Intern

Bytedance Inc.

This summer I am an intern here.
 
 
 
 
 
May 2018 – August 2018
San Jose, California

Research Intern

Adobe Research

I did the research on how to reconstruct a 3D scene for uban environments by utilizing their global regularities and symmetries. I enjoyed my time with my advisors Qi Sun, Zhili Chen, Li-Yi Wei, and Kalyan Sunkavalli.
 
 
 
 
 
May 2017 – August 2017
Venice, California

Research Intern

Snapchat Inc.

I worked on a project about algorithm-based Beatles-style MIDI music composition with the help from an outstanding composer and percussionist Sam Young at UCLA. I was advised by Wei Chu and Xin Chen.
 
 
 
 
 
May 2016 – August 2016
Los Gatos, California

Research Intern

Bellus 3D Inc.

During the internship, I implemented a software to deform a face mesh to fit the point cloud of a scanned face along with the Morphable Face Model. I was advised by James Davis and Jin Liu.
 
 
 
 
 
September 2015 – Present
Berkeley, California

Research Assistant

University of California, Berkeley

I am currently pursuing my Ph.D. degree here.
 
 
 
 
 
December 2013 – June 2015
Beijing

Research Assistant

Tsinghua University

Advised by Jianyang Zeng, I did research related to the proteins’ 3D structures in the Machine Learning and Computational Biology Group at IIIS when I was a undergraduate. I designed fast and massively parallel combinotorial search algorithms and tested them on the protein design problems. I also implemented a CUDA version of RELION to accelerate the 3D reconstruction of protein structures from cryo-microscopy images, which later turned into my undergraduate thesis.
 
 
 
 
 
August 2013 – November 2013
Beijing

Research Intern

Microsoft Research Asia

I was a research intern in the Natural Language Processing Group at MSRA, advised by Jianwen Zhang. I studied method of applying Markov Logic Network for the knowledge database completion problem to fill in the missing entires in Freebase.

Service

I was a teaching assistant of the following courses at UC Berkeley:

Skills

Python

Deep Learning

C++

CUDA

Blender 3D

OpenGL/GLSL