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

Recovering full 3D shapes from partial observations is a challenging taskthat has been extensively addressed in the computer vision community. Many deeplearning methods tackle this problem by training 3D shape generation networksto learn a prior over the full 3D shapes. In this training regime, the methodsexpect the inputs to be in a fixed canonical form, without which they fail tolearn a valid prior over the 3D shapes. We propose SCARP, a model that performsShape Completion in ARbitrary Poses. Given a partial pointcloud of an object,SCARP learns a disentangled feature representation of pose and shape by relyingon rotationally equivariant pose features and geometric shape features trainedusing a multi-tasking objective. Unlike existing methods that depend on anexternal canonicalization, SCARP performs canonicalization, pose estimation,and shape completion in a single network, improving the performance by 45% overthe existing baselines. In this work, we use SCARP for improving graspproposals on tabletop objects. By completing partial tabletop objects directlyin their observed poses, SCARP enables a SOTA grasp proposal network improvetheir proposals by 71.2% on partial shapes. Project page:https://bipashasen.github.io/scarp

SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping