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 a method that can recognize new objects and estimate their 3D posein RGB images even under partial occlusions. Our method requires neither atraining phase on these objects nor real images depicting them, only their CADmodels. It relies on a small set of training objects to learn local objectrepresentations, which allow us to locally match the input image to a set of"templates", rendered images of the CAD models for the new objects. In contrastwith the state-of-the-art methods, the new objects on which our method isapplied can be very different from the training objects. As a result, we arethe first to show generalization without retraining on the LINEMOD andOcclusion-LINEMOD datasets. Our analysis of the failure modes of previoustemplate-based approaches further confirms the benefits of local features fortemplate matching. We outperform the state-of-the-art template matching methodson the LINEMOD, Occlusion-LINEMOD and T-LESS datasets. Our source code and dataare publicly available at https://github.com/nv-nguyen/template-pose

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions