Liu He

I am a PhD candidate at Purdue University. My PhD advisor is Daniel Aliaga. I am interested in integrating advanced techniques to broad interdisciplinary CV/CG problems. My research focuses on generation, reconstruction, and representation learning of 3D scenes. I am currently working on multi-modal LLMs for the graphics pipeline (modeling, rigging, and rendering) through physical-based 3D Engine.

Email  /  CV  /  GitHub  /  Google Scholar  /  LinkedIn

profile photo

Research
project image

Multi-modal LLMs Agentical Workflow for physical-based 3D Graphic Pipeline


Liu He, Xin Zhou
On-Going Internship

project image

Context-Sensitive City-Scale Urban Layout Generation using Graph Masked Autoencoder


Liu He, Daniel Aliaga
Under Reivew (2024)
> proj > paper (Coming Soon)

project image

GlobalMapper: Arbitrary-Shaped Urban Layout Generation


Liu He, Daniel Aliaga
ICCV 2023
> proj > paper > supp > code

project image

Diffusion-based document layout generation


Liu He, Yijuan Lu, John Corring, Dinei Florencio, Cha Zhang
ICDAR 2023 Oral
> proj > paper > code

project image

Generative building feature estimation from satellite images


Liu He, Jie Shan, Daniel Aliaga
IEEE Transactions on Geoscience and Remote Sensing (2023)
> proj > paper

project image

Deep learning-based urban morphology for city-scale environmental modeling


Pratiman Patel, Rajesh Kalyanam, Liu He, Daniel Aliaga, Dev Niyogi
PNAS Nexus (2023)
> proj > paper







Hobbies

Struggling to be the best anlger among CS PhDs :-).

> News about me

Cool sites from Jon Barron's website. Thanks for Leonid Keselman's Jekyll template