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 present NeuSE, a novel Neural SE(3)-Equivariant Embedding for objects, andillustrate how it supports object SLAM for consistent spatial understandingwith long-term scene changes. NeuSE is a set of latent object embeddingscreated from partial object observations. It serves as a compact point cloudsurrogate for complete object models, encoding full shape information whiletransforming SE(3)-equivariantly in tandem with the object in the physicalworld. With NeuSE, relative frame transforms can be directly derived frominferred latent codes. Our proposed SLAM paradigm, using NeuSE for object shapeand pose characterization, can operate independently or in conjunction withtypical SLAM systems. It directly infers SE(3) camera pose constraints that arecompatible with general SLAM pose graph optimization, while also maintaining alightweight object-centric map that adapts to real-world changes. Our approachis evaluated on synthetic and real-world sequences featuring changed objectsand shows improved localization accuracy and change-aware mapping capability,when working either standalone or jointly with a common SLAM pipeline.

NeuSE: Neural SE(3)-Equivariant Embedding for Consistent Spatial Understanding with Objects