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

Object pose estimation is a necessary prerequisite for autonomous roboticmanipulation, but the presence of symmetry increases the complexity of the poseestimation task. Existing methods for object pose estimation output a single 6Dpose. Thus, they lack the ability to reason about symmetries. Lately, modelingobject orientation as a non-parametric probability distribution on the SO(3)manifold by neural networks has shown impressive results. However, acquiringlarge-scale datasets to train pose estimation models remains a bottleneck. Toaddress this limitation, we introduce an automatic pose labeling scheme. GivenRGB-D images without object pose annotations and 3D object models, we design atwo-stage pipeline consisting of point cloud registration andrender-and-compare validation to generate multiple symmetricalpseudo-ground-truth pose labels for each image. Using the generated poselabels, we train an ImplicitPDF model to estimate the likelihood of anorientation hypothesis given an RGB image. An efficient hierarchical samplingof the SO(3) manifold enables tractable generation of the complete set ofsymmetries at multiple resolutions. During inference, the most likelyorientation of the target object is estimated using gradient ascent. Weevaluate the proposed automatic pose labeling scheme and the ImplicitPDF modelon a photorealistic dataset and the T-Less dataset, demonstrating theadvantages of the proposed method.

Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels