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

Prior work on 6-DoF object pose estimation has largely focused oninstance-level processing, in which a textured CAD model is available for eachobject being detected. Category-level 6-DoF pose estimation represents animportant step toward developing robotic vision systems that operate inunstructured, real-world scenarios. In this work, we propose a single-stage,keypoint-based approach for category-level object pose estimation that operateson unknown object instances within a known category using a single RGB image asinput. The proposed network performs 2D object detection, detects 2D keypoints,estimates 6-DoF pose, and regresses relative bounding cuboid dimensions. Thesequantities are estimated in a sequential fashion, leveraging the recent idea ofconvGRU for propagating information from easier tasks to those that are moredifficult. We favor simplicity in our design choices: generic cuboid vertexcoordinates, single-stage network, and monocular RGB input. We conductextensive experiments on the challenging Objectron benchmark, outperformingstate-of-the-art methods on the 3D IoU metric (27.6% higher than the MobilePosesingle-stage approach and 7.1% higher than the related two-stage approach).

Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image