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

Prior methods that tackle the problem of generalizable object pose estimationhighly rely on having dense views of the unseen object. By contrast, we addressthe scenario where only a single reference view of the object is available. Ourgoal then is to estimate the relative object pose between this reference viewand a query image that depicts the object in a different pose. In thisscenario, robust generalization is imperative due to the presence of unseenobjects during testing and the large-scale object pose variation between thereference and the query. To this end, we present a newhypothesis-and-verification framework, in which we generate and evaluatemultiple pose hypotheses, ultimately selecting the most reliable one as therelative object pose. To measure reliability, we introduce a 3D-awareverification that explicitly applies 3D transformations to the 3D objectrepresentations learned from the two input images. Our comprehensiveexperiments on the Objaverse, LINEMOD, and CO3D datasets evidence the superioraccuracy of our approach in relative pose estimation and its robustness inlarge-scale pose variations, when dealing with unseen objects.

3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation