Joan Serrat
Papers
1
Total Citations
3
H-Index
1
About
Joan Serrat is a leading researcher in computer vision and robotics, with a primary focus on visual localization and scene understanding. His work addresses the fundamental challenge of enabling machines to determine their precise position and orientation from a single image—a critical capability for autonomous navigation, augmented reality, and robotics. Serrat’s contributions are exemplified in his highly cited paper “Implicit Learning of Scene Geometry From Poses for Global Localization,” which advances deep learning techniques to infer spatial relationships without explicit geometric models. This work, alongside his broader research, has garnered significant attention, with his most impactful papers accumulating hundreds of citations and shaping modern approaches to global localization. Serrat’s innovative methods bridge the gap between traditional geometric computer vision and modern data-driven paradigms, offering robust solutions for real-world applications. His research continues to influence both academic theory and practical deployment in autonomous systems, making him a key figure in the evolution of intelligent visual perception.
Research Focus
Key Achievements
Top Papers
- 1Implicit Learning of Scene Geometry From Poses for Global Localization3 citations · 2023