The Spatial AI Lab (SAIL), led by Lei Li, focuses on empowering machines with spatial intelligence to perceive, understand, and interact with 3D worlds, both virtual and real, in a way that mirrors human spatial reasoning. Our research is at the intersection of computer vision, computer graphics, and artificial intelligence. We work on data-efficient learning techniques combined with geometric principles to reason about 3D worlds and the relations within them, advancing areas including scene reconstruction, human-scene interaction, human movement analysis, 3D shape analysis, geometric transfer learning, and 3D generative models.
Research Tags: Spatial Intelligence; Generative AI; Foundation Models; Human-Centered Computing; Computer Vision; Computer Graphics; Geometric Deep Learning
