KVN: Keypoints Voting Network with Differentiable RANSAC for Stereo Pose Estimation

arXiv:2307.11543v2 Announce Type: replace
Abstract: Object pose estimation is a fundamental computer vision task exploited in several robotics and augmented reality applications. Many established approaches rely on predicting 2D-3D keypoint correspondences using RANSAC (Random sample consensus) and estimating the object pose using the PnP (Perspective-n-Point) algorithm. Being RANSAC non-differentiable, correspondences cannot be directly learned in an end-to-end fashion. In this paper, we address the stereo image-based object pose estimation problem by i) introducing a differentiable RANSAC layer into a well-known …

abstract algorithm applications arxiv augmented reality computer computer vision consensus cs.cv cs.ro differentiable network perspective pnp random reality robotics sample type vision voting