Gianfranco Doretto

West Virginia University

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

2
H-Index
2
Papers
29
Total Citations
15
Avg Citations/Paper
🏆 Most Cited Paper
Open-Fusion: Real-time Open-Vocabulary 3D Mapping and Queryable Scene Representation
22 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 10
🏛 Institutions: West Virginia University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago