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

Category-level object pose estimation aims to find 6D object poses ofpreviously unseen object instances from known categories without access toobject CAD models. To reduce the huge amount of pose annotations needed forcategory-level learning, we propose for the first time a self-supervisedlearning framework to estimate category-level 6D object pose from single 3Dpoint clouds.During training, our method assumes no ground-truth poseannotations, no CAD models, and no multi-view supervision. The key to ourmethod is to disentangle shape and pose through an invariant shapereconstruction module and an equivariant pose estimation module, empowered bySE(3) equivariant point cloud networks.The invariant shape reconstructionmodule learns to perform aligned reconstructions, yielding a category-levelreference frame without using any annotations. In addition, the equivariantpose estimation module achieves category-level pose estimation accuracy that iscomparable to some fully supervised methods. Extensive experiments demonstratethe effectiveness of our approach on both complete and partial depth pointclouds from the ModelNet40 benchmark, and on real depth point clouds from theNOCS-REAL 275 dataset. The project page with code and visualizations can befound at: https://dragonlong.github.io/equi-pose.

Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimation