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

In this paper, we present an accurate yet effective solution for 6D poseestimation from an RGB image. The core of our approach is that we firstdesignate a set of surface points on target object model as keypoints and thentrain a keypoint detector (KPD) to localize them. Finally a PnP algorithm canrecover the 6D pose according to the 2D-3D relationship of keypoints. Differentfrom recent state-of-the-art CNN-based approaches that rely on a time-consumingpost-processing procedure, our method can achieve competitive accuracy withoutany refinement after pose prediction. Meanwhile, we obtain a 30% relativeimprovement in terms of ADD accuracy among methods without using refinement.Moreover, we succeed in handling heavy occlusion by selecting the mostconfident keypoints to recover the 6D pose. For the sake of reproducibility, wewill make our code and models publicly available soon.

Estimating 6D Pose From Localizing Designated Surface Keypoints