Max Robotics — Global Service Robot Directory + US Certification

About

Daniel Cohen-Or is a pioneering force in computer graphics and geometric modeling, whose work has fundamentally reshaped how we acquire, reconstruct, and understand 3D shapes. His research masterfully bridges autonomous scanning, shape analysis, and computational geometry, creating intelligent systems that don't just capture geometry, but actively reason about it. Cohen-Or's landmark contributions include quality-driven scanning strategies that prioritize fidelity over coverage, as demonstrated in his highly-cited "Quality-driven Poisson-guided autoscanning" (78 citations), which ensures high-quality model acquisition by intelligently placing scans. He further advanced the field with attention-driven depth acquisition for object identification (49 citations), enabling robots to autonomously explore and identify unknown objects from vast shape collections. His work on autonomous indoor scene reconstruction using time-varying tensor fields (47 citations) tackles the critical balance between exploration efficiency and reconstruction quality for mobile robots. Perhaps most creatively, Cohen-Or introduced the "Dip transform" (15 citations), a novel shape reconstruction method inspired by Archimedes' principle, demonstrating his unique ability to draw from classical physics to solve modern computational problems. Through these innovations, Cohen-Or has established himself as a visionary whose work continues to inspire new generations of researchers in 3D computer vision and graphics.