English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Object pose estimation is a fundamental computer vision task exploited inseveral robotics and augmented reality applications. Many establishedapproaches 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 thispaper, we address the stereo image-based object pose estimation problem by (i)introducing a differentiable RANSAC layer into a well-known monocular poseestimation network; (ii) exploiting an uncertainty-driven multi-view PnP solverwhich can fuse information from multiple views. We evaluate our approach on achallenging public stereo object pose estimation dataset, yieldingstate-of-the-art results against other recent approaches. Furthermore, in ourablation study, we show that the differentiable RANSAC layer plays asignificant role in the accuracy of the proposed method. We release with thispaper the open-source implementation of our method.

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