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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We address the task of 6D multi-object pose: given a set of known 3D objectsand an RGB or RGB-D input image, we detect and estimate the 6D pose of eachobject. We propose a new approach to 6D object pose estimation which consistsof an end-to-end differentiable architecture that makes use of geometricknowledge. Our approach iteratively refines both pose and correspondence in atightly coupled manner, allowing us to dynamically remove outliers to improveaccuracy. We use a novel differentiable layer to perform pose refinement bysolving an optimization problem we refer to as Bidirectional Depth-AugmentedPerspective-N-Point (BD-PnP). Our method achieves state-of-the-art accuracy onstandard 6D Object Pose benchmarks. Code is available athttps://github.com/princeton-vl/Coupled-Iterative-Refinement.

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation