Hsueh-Ti Derek Liu

I am an incoming Research Scientist at Roblox Research. Currently, I am a Ph.D. candidate at the University of Toronto studying digital geometry processing. My research mainly focuses on developing easy-to-use 3D modeling tools with data-driven approaches and numerical methods for processing geometric data at scale. My research is partially supported by the Adobe Research Fellowship. My PhD is advised by Prof. Alec Jacobson. I completed my M.S. with Profs. Keenan Crane and Levent Burak Kara at Carnegie Mellon University, and my B.S.E. at National Taiwan University. Recently, I am co-organizing a webseries about geometry processing – Toronto Geometry Colloquium.

E-mail: hsuehtil@cs.toronto.edu


Learning Smooth Neural Functions via Lipschitz Regularization
Hsueh-Ti Derek Liu, Francis Williams, Alec Jacobson, Sanja Fidler, Or Litany
SIGGRAPH North America, 2022
Paper (14MB) ArXiv Project Code Talk (coming soon)

Kubric: A scalable dataset generator
Klaus Greff, Francois Belletti, Lucas Beyer, Carl Doersch, Yilun Du, Daniel Duckworth, David J Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam Laradji, Hsueh-Ti Derek Liu, Henning Meyer, Yishu Miao, Derek Nowrouzezahrai, Cengiz Oztireli, Etienne Pot, Noha Radwan, Daniel Rebain, Sara Sabour, Mehdi S. M. Sajjadi, Matan Sela, Vincent Sitzmann, Austin Stone, Deqing Sun, Suhani Vora, Ziyu Wang, Tianhao Wu, Kwang Moo Yi, Fangcheng Zhong, Andrea Tagliasacchi
CVPR, 2022
Paper Project Code

Surface Multigrid via Intrinsic Prolongation
Hsueh-Ti Derek Liu, Jiayi Eris Zhang, Mirela Ben-Chen, Alec Jacobson
ACM Transactions on Graphics (SIGGRAPH North America), 2021
Paper (65MB) ArXiv Project Code Talk

An Introduction to Deep Learning on Meshes
Rana Hanocka, Hsueh-Ti Derek Liu
SIGGRAPH (North America & Asia) Course, 2021
Website Video

Normal-Driven Spherical Shape Analogies
Hsueh-Ti Derek Liu, Alec Jacobson
Computer Graphics Forum (SGP), 2021
Paper (74MB) ArXiv Talk Code (MATLAB) Code (C++)

An Introduction to Geometry Processing Programming in MATLAB with gptoolbox
Hsueh-Ti Derek Li, Silvia Sellán, Oded Stein (Advised by Alec Jacobson)
Computer Graphics Forum (SGP), 2021
Website Talk Code (MATLAB)

Chordal Decomposition for Spectral Coarsening
Honglin Chen, Hsueh-Ti Derek Liu, Alec Jacobson, David I.W. Levin
ACM Transactions on Graphics (SIGGRAPH Asia), 2020
Paper (81MB) Project Code

Neural Subdivision
Hsueh-Ti Derek Liu, Vladimir G. Kim, Siddhartha Chaudhuri, Noam Aigerman, Alec Jacobson
ACM Transactions on Graphics (SIGGRAPH North America), 2020
Paper (95MB) ArXiv Project Code Talk

Spectral Mesh Simplification
Thibault Lescoat, Hsueh-Ti Derek Liu, Jean-Marc Thiery, Alec Jacobson, Tamy Boubekeur, Maks Ovsjanikov
Computer Graphics Forum (Eurographics), 2020
Paper (35MB) Code (C++)

Cubic Stylization
Hsueh-Ti Derek Liu, Alec Jacobson
ACM Transactions on Graphics (SIGGRAPH Asia), 2019
Paper (98MB) ArXiv Project Video Code (MATLAB) Code (C++)

Spectral Coarsening of Geometric Operators
Hsueh-Ti Derek Liu, Alec Jacobson, Maks Ovsjanikov
ACM Transactions on Graphics (SIGGRAPH North America), 2019
Paper (78MB) ArXiv Project Talk Code (MATLAB)

Beyond Pixel Norm-Balls:
Parametric Adversaries using an Analytically Differentiable Renderer
Hsueh-Ti Derek Liu, Michael Tao, Chun-Liang Li, Derek Nowrouzezahrai, Alec Jacobson
ICLR 2019
Paper (3MB) ArXiv Poster

Paparazzi: Surface Editing by way of Multi-View Image Processing
Hsueh-Ti Derek Liu, Michael Tao, Alec Jacobson
ACM Transactions on Graphics (SIGGRAPH Asia), 2018
Paper (37MB) Paper (6MB) Project Code (Python)

A Dirac Operator for Extrinsic Shape Analysis
Hsueh-Ti Derek Liu, Alec Jacobson, Keenan Crane
Computer Graphics Forum (SGP), 2017
Paper (6MB) Project Code (MATLAB)


This mesh MNIST dataset serves as the Hello World dataset of mesh deep learning. It contains thousands of 3D meshes of handwritten digits. This dataset is created from the image MNIST.


Blender toolbox
This contains a set of Python scripts for rendering 3D shapes in Blender, designed to efficiently render paper figures. This toolbox is still under development, if any questions or recommendations, please contact me via email.

This is a collection of basic geometry processing functions constructed to work with JAX’s autodifferentiation feature for geometric machine learning.