Jiahao Li

avatar I am a PhD student at TTIC advised by Greg Shakhnarovich in the PALS Lab. I primarily work on 3D computer vision and generative models. Before coming to TTIC, I received my Master of Computer Science from Washington University in St. Louis, advised by Ayan Chakrabarti. I got my Bachelor of Mathematics from Sun Yat-sen University. I have interned at Adobe Resarch, Meta Reality Labs and Megvii.
github scholar linkedin email
avatar

Research

For ease of maintenance, only the most representative works are shown here. See my Google Scholar page for a full list of publications.

FastMap: Revisiting Dense and Scalable Structure from Motion

Jiahao Li*, Haochen Wang*, Muhammad Zubair Irshad, Igor Vasiljevic, Matthew R. Walter, Vitor Campagnolo Guizilini, Greg Shakhnarovich
project page | arXiv | code
Arxiv 2025
A fast structure from motion pipeline written in PyTorch.

Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model

Jiahao Li, Hao Tan, Kai Zhang, Zexiang Xu, Fujun Luan, Yinghao Xu, Yicong Hong, Kalyan Sunkavalli, Greg Shakhnarovich, Sai Bi
project page | arXiv
ICLR 2024
High quality, diverse and Janus-free Text-to-3D in 20 SECONDS.

Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation

Haochen Wang*, Xiaodan Du*, Jiahao Li*, Raymond A. Yeh, Greg Shakhnarovich
project page | arXiv | code
CVPR 2023
Generating 3D objects from 2D diffusion models by chaining scores with NeRF gradients.
Jiahao Li © 2025