RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy

no code implementations • 18 Sep 2023 • Mert Asim Karaoglu, Viktoria Markova, Nassir Navab, Benjamin Busam, Alexander Ladikos

While most classical methods achieve rotation-equivariant detection and invariant description by design, many learning-based approaches learn to be robust only up to a certain degree.

Keypoint Detection Self-Supervised Learning

Global Multi-modal 2D/3D Registration via Local Descriptors Learning

no code implementations • 6 May 2022 • Viktoria Markova, Matteo Ronchetti, Wolfgang Wein, Oliver Zettinig, Raphael Prevost

Multi-modal registration is a required step for many image-guided procedures, especially ultrasound-guided interventions that require anatomical context.