Ziwei Liao

Ziwei Liao

Ph.D. Candidate, University of Toronto

Home

Biography

Hi, welcome! I am Ziwei Liao, currently a 3rd-year Ph.D. candidate in computer vision and robotics, at the Toronto Robotics & AI Lab, Institute for Aerospace Study (UTIAS), University of Toronto, supervised by Prof. Steven L. Waslander. I am affiliated with the Vector Institute, and the University of Toronto Robotics Institute.

I was fortunate to have cooperated with researchers at Microsoft Research Asia (MSRA), and Megvii Research (Face++).

In 2021, I received my M.Sci. at the Autonomous Robots Lab, supervised by Prof. Wang Wei, at the Robotics Institute, School of Mechanical Engineering and Automation of Beihang University, Beijing, China.

In 2018, I received my B.E. in Mechatronics Engineering from Beihang University, where I also visited the Intelligent Robot Laboratory at Tsukuba University, Japan as a research assistant supervised by Prof. Akihisa Ohya.

Please refer to my [CV] for more details.

Research Interests

Keywords: 3D Vision, SLAM, Robotics, Deep Learning

My long-term goal is to make intelligent robots and machines perceive, understand, and interact with real environments to help human beings in the real world. To achieve that, my research concentrates on visual perception and learning as following:

3D Objects and Scenes: My research areas cover mapping and localization (SLAM), pose estimation, and reconstruction, with a focus on 3D common objects.

Learning with 3D geometry: I am interested in the combination of geometrics and learning-based methods, such as Neural Radience Fields (NeRF), Generative Models as 3D shape priors (e.g., VAE, Diffusion), learning frameworks for multi-view and 3D (e.g., Transformers), and modeling of the distribution and uncertainty.

If you are also interested, feel free to contact me for a small talk or collaboration!

News

[2/2024] A paper for 3D Human Pose Estimation with Transformers is accepted by CVPR 24, cooperated with Microsoft Research Asia. See you in Seattle, USA in June!

[1/2024] A paper for object-level mapping (3D pose & shape) with uncertainty is accepted by ICRA 24. See you in Japan in May!

[10/2023] A paper for 3D object reconstruction with uncertainty was accepted by WACV 2024, held in Hawaii, USA.

[2/2022] A paper for monocular object-level SLAM with quadrics (SO-SLAM) was accepted by IEEE RA-L and presented at ICRA 2022.

[9/2021] I joined the Toronto Robotics and AI Lab at the University of Toronto to pursue a Ph.D. in computer vision and robotics.

…

Academic Service

I am serving as a reviewer for:

  • Journal: The International Journal of Robotics Research (IJRR), IEEE Robotics and Automation Letters (RA-L)
  • Conference: ICRA 2024, 2023; CVPR 2024, 2023; ECCV 2024; WACV 2024;

Publications

Please refer to the page Research or My Google Scholar for more details.