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

Rotation estimation of high precision from an RGB-D object observation is ahuge challenge in 6D object pose estimation, due to the difficulty of learningin the non-linear space of SO(3). In this paper, we propose a novel rotationestimation network, termed as VI-Net, to make the task easier by decoupling therotation as the combination of a viewpoint rotation and an in-plane rotation.More specifically, VI-Net bases the feature learning on the sphere with twoindividual branches for the estimates of two factorized rotations, where aV-Branch is employed to learn the viewpoint rotation via binary classificationon the spherical signals, while another I-Branch is used to estimate thein-plane rotation by transforming the signals to view from the zenithdirection. To process the spherical signals, a Spherical Feature PyramidNetwork is constructed based on a novel design of SPAtial Spherical Convolution(SPA-SConv), which settles the boundary problem of spherical signals viafeature padding and realizesviewpoint-equivariant feature extraction bysymmetric convolutional operations. We apply the proposed VI-Net to thechallenging task of category-level 6D object pose estimation for predicting theposes of unknown objects without available CAD models; experiments on thebenchmarking datasets confirm the efficacy of our method, which outperforms theexisting ones with a large margin in the regime of high precision.

VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations