George Eskandar
Papers
1
Total Citations
6
H-Index
1
About
George Eskandar is a leading researcher in the field of 3D perception for autonomous systems, with a primary focus on the robustness and generalization of LiDAR-based 3D object detectors. His work addresses a critical bottleneck in deploying autonomous driving technology: the severe performance degradation of these detectors when encountering unseen environments, such as different cities or weather conditions. In his highly influential 2024 study, "An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains," Eskandar systematically analyzed the failure modes of state-of-the-art models, revealing that domain shifts in point cloud density and geometry are the primary culprits. This work, which has already garnered 6 citations, provides a foundational benchmark and diagnostic framework for the field. By identifying the specific weaknesses of current architectures, Eskandar’s research is paving the way for more reliable and adaptable perception systems, a crucial step toward safe and scalable autonomous driving. His contributions are essential reading for any student or researcher working on domain generalization or robust 3D vision.
Research Focus
Key Achievements
Top Papers
- 1