Papers
2
Total Citations
58
H-Index
2
About
Arthur Moreau is a leading researcher in robotics and autonomous vehicle localization, with a focus on deep learning-based visual perception. His work centers on developing reliable, uncertainty-aware methods for camera re-localization—a critical challenge for real-world navigation systems. In his highly cited 2022 paper, "CoordiNet," Moreau introduced a CNN-based pose regressor that directly predicts 3D translation and rotation from a single image, while also providing uncertainty estimates to enhance robustness in dynamic environments. This work has garnered 41 citations and is foundational for safe, trustworthy autonomous driving. Moreau further advanced the field with his 2021 paper, "LENS," which pioneered the use of Neural Radiance Fields (NeRF) for robot relocalization. By generating synthetic novel views, his method significantly improved camera pose regression accuracy, demonstrating how cutting-edge view synthesis can enhance classical localization pipelines. With over 58 combined citations and a clear trajectory of innovation, Moreau is shaping the next generation of reliable, perception-driven navigation systems for robotics and autonomous vehicles.
Research Focus
Key Achievements
Top Papers
- 1
- 2LENS: Localization enhanced by NeRF synthesis17 citations · 2021