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

We present GigaPose, a fast, robust, and accurate method for CAD-based novelobject pose estimation in RGB images. GigaPose first leverages discriminativetemplates, rendered images of the CAD models, to recover the out-of-planerotation and then uses patch correspondences to estimate the four remainingparameters. Our approach samples templates in only a two-degrees-of-freedomspace instead of the usual three and matches the input image to the templatesusing fast nearest neighbor search in feature space, results in a speedupfactor of 38x compared to the state of the art. Moreover, GigaPose issignificantly more robust to segmentation errors. Our extensive evaluation onthe seven core datasets of the BOP challenge demonstrates that it achievesstate-of-the-art accuracy and can be seamlessly integrated with a refinementmethod. Additionally, we show the potential of GigaPose with 3D modelspredicted by recent work on 3D reconstruction from a single image, relaxing theneed for CAD models and making 6D pose object estimation much more convenient.Our source code and trained models are publicly available athttps://github.com/nv-nguyen/gigaPose

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence