A case for using rotation invariant features in state of the art feature matchers
Georg Bökman, Fredrik Kahl
20222022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)44 citationsDOI
Abstract
The aim of this paper is to demonstrate that a state of the art feature matcher (LoFTR) can be made more robust to rotations by simply replacing the backbone CNN with a steerable CNN which is equivariant to translations and image rotations. It is experimentally shown that this boost is obtained without reducing performance on ordinary illumination and viewpoint matching sequences.
Topics & Concepts
Equivariant mapInvariant (physics)Artificial intelligenceFeature matchingFeature (linguistics)Rotation (mathematics)Computer scienceComputer visionPattern recognition (psychology)Image matchingFeature extractionMathematicsImage (mathematics)Pure mathematicsLinguisticsPhilosophyMathematical physicsRobotics and Sensor-Based LocalizationAdvanced Image and Video Retrieval TechniquesAdvanced Vision and Imaging