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

Most learning-based approaches to category-level 6D pose estimation aredesign around normalized object coordinate space (NOCS). While beingsuccessful, NOCS-based methods become inaccurate and less robust when handlingobjects of a category containing significant intra-category shape variations.This is because the object coordinates induced by global and rigid alignment ofobjects are semantically incoherent, making the coordinate regression hard tolearn and generalize. We propose Semantically-aware Object Coordinate Space(SOCS) built by warping-and-aligning the objects guided by a sparse set ofkeypoints with semantically meaningful correspondence. SOCS is semanticallycoherent: Any point on the surface of a object can be mapped to a semanticallymeaningful location in SOCS, allowing for accurate pose and size estimationunder large shape variations. To learn effective coordinate regression to SOCS,we propose a novel multi-scale coordinate-based attention network. Evaluationsdemonstrate that our method is easy to train, well-generalizing for largeintra-category shape variations and robust to inter-object occlusions.

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations