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

Traditional geometric registration based estimation methods only exploit theCAD model implicitly, which leads to their dependence on observation qualityand deficiency to occlusion. To address the problem,the paper proposes abidirectional correspondence prediction network with a point-wiseattention-aware mechanism. This network not only requires the model points topredict the correspondence but also explicitly models the geometricsimilarities between observations and the model prior. Our key insight is thatthe correlations between each model point and scene point provide essentialinformation for learning point-pair matches. To further tackle the correlationnoises brought by feature distribution divergence, we design a simple buteffective pseudo-siamese network to improve feature homogeneity. Experimentalresults on the public datasets of LineMOD, YCB-Video, and Occ-LineMOD show thatthe proposed method achieves better performance than other state-of-the-artmethods under the same evaluation criteria. Its robustness in estimating posesis greatly improved, especially in an environment with severe occlusions.

Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction