Justin Solomon
Papers
2
Total Citations
1,128
H-Index
2
About
Justin Solomon is a leading researcher in geometric and topological data analysis, with a particular focus on computer vision and machine learning for 3D data. His most influential contribution is the development of "Deep Closest Point" (DCP), a groundbreaking framework that reimagines the classic Iterative Closest Point (ICP) algorithm for point cloud registration using deep learning. DCP learns rich, data-driven representations for aligning 3D point clouds, a critical task in robotics, autonomous navigation, and medical imaging. The work has been cited over 1,100 times, cementing its status as a foundational method in the field. Beyond DCP, Solomon's research spans optimal transport, shape analysis, and geometric optimization, often bridging theoretical rigor with practical algorithms. He is an Associate Professor at MIT and leads the Geometric Data Processing Group, where his work has earned accolades including an NSF CAREER Award and an MIT Junior Bose Award. For students and researchers, Solomon's work exemplifies how deep learning can transform classical geometric problems into powerful, scalable solutions.
Research Focus
Key Achievements
Top Papers
- 1Deep Closest Point: Learning Representations for Point Cloud Registration1,008 citations · 2019
- 2Deep Closest Point: Learning Representations for Point Cloud Registration120 citations · 2019