Gianfranco Doretto
Papers
2
Total Citations
29
H-Index
2
About
Gianfranco Doretto is a leading researcher in computer vision and robotics, with a focus on 3D scene understanding, semantic mapping, and feature detection. His major contributions include pioneering real-time open-vocabulary 3D mapping through Open-Fusion (2024, 22 citations), which enables robots to dynamically build and query semantic 3D maps without pre-defined concepts—a critical advance for autonomous navigation and human-robot interaction. He has also advanced self-supervised keypoint detection and matching for fisheye and perspective images (2023, 7 citations), addressing fundamental challenges in structure from motion, AR/VR, and robotics. Doretto’s work bridges the gap between semantic understanding and geometric reconstruction, making 3D mapping more flexible and efficient. His research has been recognized for its practical impact on real-time systems, and he continues to push boundaries in open-vocabulary scene representation and robust feature learning. With a strong publication record and growing citation impact, Doretto is shaping the future of intelligent perception systems that can understand and interact with complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2