Study Award of the SEW-Eurodrive Foundation ro ASL-MagicLeap Master Thesis

Paul-Edouard Sarlin's master thesis titled "“SuperGlue: Learning Feature Matching with Graph Neural Networks” has been awarded the 2020 Study Prize by the SEW-Eurodrive-Foundation. The master thesis was co-supervised by ASL and MagicLeap.

Paul-Edouard's work is a major contribution in the field visual feature matching that outperformed all learned approaches and achieved state-of-the-art results on the task of pose estimation in challenging real-world indoor and outdoor environments. His results have been published at the top conference on computer vision (CVPR 2020) as an oral presentation (5.7% acceptance rate out of 6056 submission). Furthermore, Paul-Edouard has used his approach to participate in different challenging competitions, winning 3 CVPR 2020 competitions (local features for visual localization, visual localization for handheld devices, and the image matching challenge) and 4 ECCV 2020 competitions (local features for visual localization, visual localization for handheld devices, visual localization for autonomous vehicles and the map-based visual re-localization challenge).

The SEW-Eurodrive award winners will be recognized during the virtual Ernst Blickle Lecture and Study Award Ceremony. Congratulations to the winner!