Diego Thomas
Papers
6
Total Citations
72
H-Index
3
About
Diego Thomas is a leading researcher at the intersection of 3D computer vision, robotics, and human-robot interaction. His work primarily focuses on enabling machines to perceive and interact with the physical world, with key contributions in 3D scene understanding, gesture generation for social robots, and underwater SLAM. Thomas’s most cited paper, “Fast 3D point cloud segmentation using supervoxels with geometry and color for 3D scene understanding” (2017, 45 citations), introduced a pioneering method for segmenting colored 3D point clouds, a critical low-level step for robotic applications that has become foundational in the field. He has also advanced social robotics through deep learning-based gesture generation systems, such as “Deep Gesture Generation for Social Robots Using Type-Specific Libraries” (2022, 8 citations), which enhances natural communication by enabling robots to produce contextually appropriate body language. In underwater robotics, Thomas developed a two-stage pose optimization algorithm for SLAM using color information and 3D scanning (2024), addressing the challenging domain of subsea navigation. His work on gesture integration with DIY robot kits (2022) further demonstrates his commitment to accessible, practical robotics. With a growing citation impact and a portfolio spanning perception, interaction, and autonomy, Thomas is shaping how robots see, move, and communicate in complex environments.
Research Focus
Key Achievements
Top Papers
- 1
- 23D pedestrian localization using multiple cameras: a generalizable approach11 citations · 2022
- 3Deep Gesture Generation for Social Robots Using Type-Specific Libraries8 citations · 2022
- 4
- 5
- 6ACT2G2 citations · 2023