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

We consider learning based methods for visual localization that do notrequire the construction of explicit maps in the form of point clouds orvoxels. The goal is to learn an implicit representation of the environment at ahigher, more abstract level. We propose to use a generative approach based onGenerative Query Networks (GQNs, Eslami et al. 2018), asking the followingquestions: 1) Can GQN capture more complex scenes than those it was originallydemonstrated on? 2) Can GQN be used for localization in those scenes? To studythis approach we consider procedurally generated Minecraft worlds, for which wecan generate images of complex 3D scenes along with camera pose coordinates. Wefirst show that GQNs, enhanced with a novel attention mechanism can capture thestructure of 3D scenes in Minecraft, as evidenced by their samples. We thenapply the models to the localization problem, comparing the results to adiscriminative baseline, and comparing the ways each approach captures the taskuncertainty.

Learning models for visual 3D localization with implicit mapping