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

Existing Object Pose Estimation (OPE) methods for stacked scenarios are notrobust to changes in object scale. This paper proposes a new 6DoF OPE network(NormNet) for different scale objects in stacked scenarios. Specifically, eachobject's scale is first learned with point-wise regression. Then, all objectsin the stacked scenario are normalized into the same scale through semanticsegmentation and affine transformation. Finally, they are fed into a sharedpose estimator to recover their 6D poses. In addition, we introduce a newSim-to-Real transfer pipeline, combining style transfer and domainrandomization. This improves the NormNet's performance on real data even if weonly train it on synthetic data. Extensive experiments demonstrate that theproposed method achieves state-of-the-art performance on public benchmarks andthe MultiScale dataset we constructed. The real-world experiments show that ourmethod can robustly estimate the 6D pose of objects at different scales.

NormNet: Scale Normalization for 6D Pose Estimation in Stacked Scenarios