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

Humans are able to perform fast and accurate object pose estimation evenunder severe occlusion by exploiting learned object model priors from everydaylife. However, most recently proposed pose estimation algorithms neglect toutilize the information of object models, often end up with limited accuracy,and tend to fall short in cluttered scenes. In this paper, we present a novellearning-based model, \underline{P}ose-Guided \underline{P}oint Cloud\underline{G}enerating Networks for 6D Object Pose Estimation (P$^2$GNet),designed to effectively exploit object model priors to facilitate 6D objectpose estimation. We achieve this with an end-to-end estimation-by-generationworkflow that combines the appearance information from the RGB-D image and thestructure knowledge from object point cloud to enable accurate and robust poseestimation. Experiments on two commonly used benchmarks for 6D pose estimation,YCB-Video dataset and LineMOD dataset, demonstrate that P$^2$GNet outperformsthe state-of-the-art method by a large margin and shows marked robustnesstowards heavy occlusion, while achieving real-time inference.

P$^2$GNet: Pose-Guided Point Cloud Generating Networks for 6-DoF Object Pose Estimation