Ramesh Raskar

Human Media, Massachusetts Institute of Technology

Papers

Total Citations

186

H-Index

About

Ramesh Raskar is a pioneering researcher at the intersection of computer vision, computational imaging, and robotics, whose work consistently pushes the boundaries of how machines perceive and interact with the physical world. His research spans transparent object segmentation, 3D reconstruction, and vision-guided robotics, tackling some of the most challenging open problems in visual computing. Among his most influential contributions is his reframing of transparent object segmentation through the lens of light polarization — a creative and technically sophisticated approach that has garnered 130 citations and opened new directions for a problem that had long resisted conventional texture-based methods. His earlier work on vision-guided robotic picking systems, employing multi-flash camera arrays to cast revealing shadows for 3D pose estimation, demonstrated a practical elegance that earned 54 citations and influenced applied robotics. More recently, his research on combining diffuse LiDAR with RGB imaging addresses fundamental limitations in handheld 3D scanning, targeting real-world challenges in low-light and low-texture environments. Raskar's career reflects a rare ability to bridge fundamental perception science with tangible engineering solutions, making his work relevant to students and researchers in computer vision, robotics, and augmented reality alike.