Home
Biography
Hello, I am Ziwei, currently a 4th-year Ph.D. candidate in computer vision and robotics from the University of Toronto. I studied at the Toronto Robotics and AI Lab supervised by Prof. Steven L. Waslander. I am affiliated with the Institute for Aerospace Study (UTIAS), UToronto Robotics Institute and the Vector Institute.
Starting in June 2024, I joined Niantic Labs, in London, UK, as a research intern. Niantic developed the AR game Pokémon GO and is a leading tech company in 3D mapping. I was also fortunate to have cooperated with researchers at Microsoft Research Asia (MSRA), and Megvii Research (Face++) as a research intern.
In 2021 and 2018, I received my M.Sci. and B.E. at the Robotics Institute of Beihang University, Beijing, China, supervised by Prof. Wang Wei. In 2017, I 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.
I will graduate before August 2025 and am open to positions in 3D, GenAI, Robotics, AR, and other relevant areas. Please feel free to send me an email. Thank you!
News
[9/2024] A paper for general object-level mapping with 3D diffusion model is accepted by CoRL 24. See you in Munich, Germany in November!
[6/2024] I joined Niantic Labs as a research intern in London, UK.
[2/2024] A paper for 3D human pose estimation with transformers is accepted by CVPR 24, cooperated with Microsoft Research Asia, held in Seattle, USA.
[1/2024] A paper for object-level mapping (3D pose & shape) with uncertainty is accepted by ICRA 24, held in Yokohama, Japan.
[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.
…
Research Interests
Keywords: 3D Vision, Robotics, Deep Learning
My long-term goal is to make robots and machines perceive, understand, and interact with 3D environments to help humans in the real world. My past research focuses on 3D vision and learning, including:
3D Representations for Objects and Scenes: Implicit representations (e.g., NeRF, SDF), Gaussian Splattings, and their applications in mapping and localization (SLAM), object reconstruction, and pose estimation from sensor observations.
Learning with Generative Priors and Uncertainty: Learning to solve ill-posed inverse problems with generative models (e.g., VAE, Diffusion) as prior knowledge, with applications in sparse-view reconstruction under partial observations, uncertainty estimation, and multi-view learning formulation (e.g., Transformers).
If you are also interested in any of the topics, please feel free to contact me for discussion and collaboration.
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: ICLR 2025; ICRA 2024, 2023; NeurIPS 2024; CVPR 2024, 2023; ECCV 2024; WACV 2024, 2025;
Publications
Please refer to the page Research or My Google Scholar for more details.