Max Robotics — Global Service Robot Directory + US Certification

About

Sagi Eppel is a researcher at the intersection of computer vision, robotics, and materials science, with a focus on enabling machines to perceive and interact with complex, real-world environments. His key contributions lie in developing machine learning methods for recognizing materials and vessels in chemistry lab settings, as well as tackling the notoriously difficult problem of transparent object perception. Eppel’s most cited work, "Computer Vision for Recognition of Materials and Vessels in Chemistry Lab Settings and the Vector-LabPics Data Set" (2020, 67 citations), introduced a novel approach for identifying substances inside containers and released a benchmark dataset that has become a valuable resource for the community. He further advanced the field with "MVTrans: Multi-View Perception of Transparent Objects" (2023, 29 citations), which addresses a critical gap in robotic manipulation by enabling depth and pose estimation for glass and other see-through items. His earlier work, "Seeing Glass: Joint Point Cloud and Depth Completion for Transparent Objects" (2021), proposed TranspareNet, a method that significantly improves RGB-D sensor accuracy for transparent surfaces. Through these contributions, Eppel has helped bridge the gap between laboratory automation and real-world perception, with his work cited over 100 times and influencing both academic research and practical applications in robotics and chemistry.