We study computer vision, robotics, and machine learning. Our primary interests include: 3D Vision: Single-view and multi-view 3D reconstruction, in particular, per-pixel reconstruction of geometry and motion for arbitrary in-the-wild scenes. Robotics: Mobile and dexterous manipulation, with a focus on sim-to-real. Procedural Synthetic Data: Procedural generation of 4D dynamic environments, simulation-based data generation, optimization of data generation.
PRINCETON VISION & LEARNING LAB