Riccardo Marin
Papers
1
Total Citations
20
H-Index
1
About
Riccardo Marin is a leading researcher at the intersection of computer graphics, geometric deep learning, and computational anatomy. His work focuses on developing data-driven methods to model, analyze, and manipulate complex 3D shapes, with a particular emphasis on human and biological forms. Marin’s most cited work, "Data-Driven Intra-Operative Estimation of Anatomical Attachments for Autonomous Tissue Dissection" (2021, 20 citations), introduces a novel convolutional framework that enables autonomous robotic systems to dynamically estimate tissue attachments during surgery—a critical step toward safe, automated dissection. This contribution bridges geometric modeling and robotic surgery, showcasing his ability to translate fundamental shape analysis into real-world clinical impact. Beyond this, Marin has made significant strides in neural representation learning for non-rigid shapes, including human bodies and faces, often leveraging spectral and intrinsic geometry techniques. His research has been published at top venues like SIGGRAPH, CVPR, and ECCV, and his work on differentiable rendering and shape correspondence has influenced both academic and industrial applications. With a growing citation record and a reputation for rigorous, interdisciplinary research, Marin is shaping the future of how machines understand and interact with the physical world.
Research Focus
Key Achievements
Top Papers
- 1