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

Visual relocalization aims to estimate the pose of a camera from one or moreimages. In recent years deep learning based pose regression methods haveattracted many attentions. They feature predicting the absolute poses withoutrelying on any prior built maps or stored images, making the relocalizationvery efficient. However, robust relocalization under environments with complexappearance changes and real dynamics remains very challenging. In this paper,we propose to enhance the distinctiveness of the image features by extractingthe deep relationship among objects. In particular, we extract objects in theimage and construct a deep object relation graph (ORG) to incorporate thesemantic connections and relative spatial clues of the objects. We integrateour ORG module into several popular pose regression models. Extensiveexperiments on various public indoor and outdoor datasets demonstrate that ourmethod improves the performance significantly and outperforms the previousapproaches.

Objects Matter: Learning Object Relation Graph for Robust Camera Relocalization