Daniel Ritchie

University of California, Berkeley, John Brown University

Papers

Total Citations

H-Index

About

Daniel Ritchie is a computational researcher whose work spans surgical simulation, 3D shape understanding, and human motion analysis. His early contributions focused on medical applications, notably developing algorithms for simulating surgical needle insertion and steering through deformable tissues — work that has proven highly influential in surgical training and planning, accumulating over 60 citations and supporting critical procedures such as biopsies, neurosurgery, and brachytherapy. More recently, Ritchie has turned his attention to 3D shape representation and understanding, pioneering unsupervised methods for reconstructing shapes through part retrieval and assembly, as well as detecting kinematic motion in part-segmented 3D object collections — research with direct implications for robotics, virtual world construction, and synthetic data generation. His most current work addresses the challenge of understanding bimanual human hand activities through GigaHands, a large-scale annotated dataset designed to enable the development of robust AI and robotics models. Across these diverse domains, Ritchie demonstrates a consistent drive to build foundational tools and datasets that empower downstream research, making his profile particularly valuable for students working at the intersection of computer vision, graphics, and robotics.