RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching

Udit Singh Parihar*1    Aniket Gujarathi*1    Kinal Mehta*1    Satyajit Tourani*1    Sourav Garg2    Michael Milford2    K. Madhava Krishna1   

1 Robotics Research Center, IIIT Hyderabad    2 QUT Centre for Robotics, Queensland University of Technology (QUT), Australia   

We present a novel framework that combines learning of invariant descriptors through data augmentation and orthographic viewpoint projection. We propose rotation-robust local descriptors, learnt through training data augmentation based on rotation homographies, and a correspondence ensemble technique that combines vanilla feature correspondences with those obtained through rotation-robust features. Using a range of benchmark datasets as well as contributing a new bespoke dataset for this research domain, we evaluate the effectiveness of the proposed approach on key tasks including pose estimation and visual place recognition.