Bio
Lei Li is a tenure-track Assistant Professor at the School of Data Science, University of Virginia. Before joining UVA in 2025, he was a postdoctoral researcher at the Technical University of Munich, working with Prof. Angela Dai, and at École Polytechnique / Inria, working with Prof. Maks Ovsjanikov. Lei received his PhD in Computer Science and Engineering (2020) from the Hong Kong University of Science and Technology, and his BEng in Software Engineering (2014) from Shandong University. His PhD thesis advisor was Prof. Chiew-Lan Tai. Lei's research interests are in computer vision and computer graphics, with a focus on advancing machine spatial intelligence to perceive, understand, and interact with the 3D world.
Open Positions
Our Spatial AI Lab (SAIL) is always looking for highly motivated PhD students and postdocs to work on impactful research at the intersection of computer vision, computer graphics, and artificial intelligence. If you are interested in joining us, please fill out this application form. More application details can be found in the openings flyer. PhD applicants must also apply to the UVA School of Data Science PhD Program.
Selected Publications
View All →News
View All →Our work Seen2Scene: Completing Realistic 3D Scenes with Visibility-Guided Flow has been accepted by ECCV 2026.
Our work TriFlow: Generating Artist-Like 3D Mesh Topology via Nearest-Vertex Vector Fields has been accepted by ECCV 2026.
Recognized as an Outstanding Area Chair for CVPR 2026.
Received a Gold Reviewer Award from ICML 2026.
Our work HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance has been accepted by ICML 2026.
I gave a talk on geometric intelligence at the School of Medicine, UVA.
I was invited to join the panel discussion of Physical AI: Intelligence Meets the Real World organized by Virginia Club of New York.
Received a 3Cavaliers 3.1 Funding Award as Co-PI (PI: Prof. Meghan Puglia) to advance research on mother-infant interaction analysis.
Our work PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding has been accepted by CVPR 2026.
We are organizing the first Symposium on Computer and Autonomous Vision Systems with a great line of talks on generative AI, visual representation learning, and robotic assistants.