Zhenyu Li is a computer vision researcher whose work spans 3D reconstruction, geometric scene understanding, depth estimation and generative AI, with a focus on developing scalable visual learning systems that bridge perception, reasoning and spatial intelligence.
Biography
Zhenyu Li is a Ph.D. student in Computer Science at King Abdullah University of Science and Technology (KAUST), where he is advised by Peter Wonka. Prior to joining KAUST, he earned his B.E. and M.S. degrees in Computer Science from Harbin Institute of Technology, China.
Li has authored works in depth estimation and 3D vision, including contributions such as BinsFormer, PatchFusion, PatchRefiner, Amodal Depth Anything and Depth Anything 3. His publications have appeared in leading venues including CVPR, ICCV, ECCV, ICLR, ICML, SIGGRAPH Asia, and AAAI. His research has received broad recognition from the community, accumulating more than 2,700 citations and contributing to state-of-the-art performance on several computer vision benchmarks.
Beyond academia, Li has gained industrial research experience through internships at Meta Reality Labs, ByteDance Seed, DiDi Cargo and SenseTime, where he worked on AR/VR body tracking, 3D reconstruction and autonomous driving perception technologies.
Expertise and Interests
Li's research aims to build intelligent systems capable of perceiving, reconstructing and reasoning about the three-dimensional world from visual observations. His work combines geometric modeling with modern deep learning approaches, spanning depth estimation, 3D scene reconstruction, visual generative modeling, embodied perception and multimodal reasoning. He is particularly interested in developing foundation models that unify visual perception and language-driven reasoning for applications in robotics, mixed reality and spatial AI.
Awards and Distinctions
- CEMSE Dean's List Award 2024, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), 2024
- 1st Place Award, Visual Continual Learning (VCL) 2023 Challenge, Multitask Learning for Robustness Track, ICCV 2023 Workshop, 2026
Education
- Master of Science (M.S.)
- Computer Science, Harbin Institute of Technology (HIT), China, 2023
