Thomas EnXu Li

I am a PhD student under the Department of Computer Science at the University of Toronto, advised by Prof. Raquel Urtasun. Meanwhile, I am a research scientist at Waabi working on 3D perception. I earned my B.A.Sc in Engineering Science from University of Toronto, majoring in Robotics Engineering and minoring in Artificial Intelligence .

What I value the most is creativity and productivity.

Email  /  CV  /  Google Scholar  /  Github  /  LinkedIn

profile photo
Research

I'm interested in computer vision, machine learning, and robotics. Much of my research is about 3D perception with LiDAR point clouds.

clean-usnob 4D-Former: Multimodal 4D Panoptic Segmentation
Ali Athar*, Enxu Li*, Sergio Casas, Raquel Urtasun
Conference on Robot Learning (CoRL), 2023 | Atlanta (GA), USA
bibtex / website / PDF / arXiv
clean-usnob MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory
Enxu Li, Sergio Casas, Raquel Urtasun
IEEE International Conference on Computer Vision (ICCV), 2023 | Paris, France
bibtex / website / PDF / arXiv
clean-usnob CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds
Enxu Li*, Ryan Razani*, Yixuan Xu, Bingbing Liu
IEEE International Conference on Robotics and Automation (ICRA) ,2023 | London, UK
bibtex / PDF / arXiv

clean-usnob MoSS: Monocular Shape Sensing for Continuum Robots
Chengnan Shentu*, Enxu Li*, Chaojun Chen, Puspita Triana Dewi, David Lindell, Jessica Burgner-Kahrs
IEEE Robotics and Automation Letters (RA-L) at RoboSoft 2024 | San Diego (CA), USA
arXiv

clean-usnob SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clustering
Enxu Li*, Ryan Razani*, Yixuan Xu, Bingbing Liu
IEEE International Conference on Robotics and Automation (ICRA) ,2022 | Philadelphia (PA), USA
bibtex / PDF / arXiv
clean-usnob GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network
Ryan Razani*, Ran Cheng*, Enxu Li, Ehsan Taghavi, Yuan Ren, Bingbing Liu
IEEE International Conference on Computer Vision (ICCV), 2021 | virtual
bibtex / PDF / arXiv
clean-usnob (AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network
Ran Cheng, Ryan Razani, Ehsan Taghavi, Enxu Li, Bingbing Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2021 | virtual
bibtex / PDF / arXiv
Patents
clean-usnob

System and Method for Proposal-free and Cluster-free Panoptic Segmentation of Point Clouds

Enxu Li, Ryan Razani, Bingbing Liu
2021
clean-usnob

System and Method for Panoptic Segmentation of Point Clouds

Enxu Li, Ryan Razani, Bingbing Liu
2021
clean-usnob

Methods and Systems for Deterministic Calculation of Surface Normal Vectors for Sparse Point Clouds

Enxu Li, Ryan Razani, Yuan Ren, Bingbing Liu
2021
Education
clean-usnob Ph.D in Computer Science
Department of Computer Science, University of Toronto
Sep 2022 - Present | Toronto, ON

GPA: 4.00/4.00

Supervisor: Prof. Raquel Urtasun


clean-usnob B.A.Sc in Engineering Science, Robotics
Faculty of Applied Science and Engineering, University of Toronto
Sep 2017 - Apr 2022 | Toronto, ON

Major GPA: 3.99/4.00, cGPA: 3.87/4.00
W. S. Wilson Medal [top graduating Engineering Science student], 2022
Daisy Intelligence Scholarship [top Robotics Engineering student], 2020
NSERC Undergraduate Research Award, 2019
U of T Scholar, 2017
Dean's Honour List - 2017-2022
Work Experience
clean-usnob

Research Scientist

Waabi Innovation Inc.
Aug 2022 - Present | Toronto, ON

Research and development for autonomous trucking. Focused topic: 3D perception, semantic segmentation, sensor fusion.

Projects
clean-usnob

RoboKart: An Intelligent Robotic Shopping Cart

Robotics Capstone Project, University of Toronto, Apr 2022
Technical Report / Presentation
Desgined RoboKart that can provide a complete robotic shopping experience for supermarket and grocery customers and evaluated its functionalities in Gazebo simulation environment.
clean-usnob

BALL BALL U: An Autonmous Ball Dispensing Prototype

Engineering Design Competition 2nd Place, University of Toronto, Apr 2019
Technical Report / Glance / Competition
Designed, fabricated and programmed a proof-of-concept robot prototype that autonomously detect and deploy objects to canisters.