David Gil

Papers

Total Citations

H-Index

About

David Gil is a researcher whose work sits at the intersection of 3D computer vision, robotics, and neural network architectures. His primary research focus is on developing efficient methods for processing and interpreting unorganized 3D data—a critical challenge in mobile robotics, particularly for tasks like mapping and egomotion estimation. Gil’s major contribution lies in his innovative use of Growing Neural Gas (GNG) algorithms to improve 3D feature extraction and reconstruction. His most cited paper, "Using GNG to improve 3D feature extraction—Application to 6DoF egomotion" (2012, 25 citations), demonstrates how GNG can be leveraged to build complete 3D models from raw sensor data, such as that from time-of-flight cameras and 3D lasers. This work directly addresses the problem of handling massive, unstructured point clouds, enabling more accurate six-degree-of-freedom (6DoF) egomotion estimation for autonomous systems. While his citation counts reflect a focused, early-career impact, Gil’s research represents a meaningful step toward making 3D data processing more efficient and scalable for real-world robotic applications. His work is particularly relevant for students and researchers interested in the intersection of unsupervised learning and spatial perception in robotics.