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

While much progress has been made in 6-DoF object pose estimation from asingle RGB image, the current leading approaches heavily rely onreal-annotation data. As such, they remain sensitive to severe occlusions,because covering all possible occlusions with annotated data is intractable. Inthis paper, we introduce an approach to robustly and accurately estimate the6-DoF pose in challenging conditions and without using any real poseannotations. To this end, we leverage the intuition that the poses predicted bya network from an image and from its counterpart synthetically altered to mimicocclusion should be consistent, and translate this to a self-supervised lossfunction. Our experiments on LINEMOD, Occluded-LINEMOD, YCB and newRandomization LINEMOD dataset evidence the robustness of our approach. Weachieve state of the art performance on LINEMOD, and OccludedLINEMOD in withoutreal-pose setting, even outperforming methods that rely on real annotationsduring training on Occluded-LINEMOD.

Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotations