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

Estimating the pose of an unseen object is the goal of the challengingone-shot pose estimation task. Previous methods have heavily relied on featurematching with great success. However, these methods are often inefficient andlimited by their reliance on pre-trained models that have not be designedspecifically for pose estimation. In this paper we propose PoseMatcher, anaccurate model free one-shot object pose estimator that overcomes theselimitations. We create a new training pipeline for object to image matchingbased on a three-view system: a query with a positive and negative templates.This simple yet effective approach emulates test time scenarios by cheaplyconstructing an approximation of the full object point cloud during training.To enable PoseMatcher to attend to distinct input modalities, an image and apointcloud, we introduce IO-Layer, a new attention layer that efficientlyaccommodates self and cross attention between the inputs. Moreover, we proposea pruning strategy where we iteratively remove redundant regions of the targetobject to further reduce the complexity and noise of the network whilemaintaining accuracy. Finally we redesign commonly used pose refinementstrategies, zoom and 2D offset refinements, and adapt them to the one-shotparadigm. We outperform all prior one-shot pose estimation methods on theLinemod and YCB-V datasets as well achieve results rivaling recentinstance-level methods. The source code and models are available athttps://github.com/PedroCastro/PoseMatcher.

PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching