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 the problem of planning views for a robot to acquire images of anobject for visual inspection and reconstruction. In contrast to offline methodswhich require a 3D model of the object as input or online methods which rely ononly local measurements, our method uses a neural network which encodes shapeinformation for a large number of objects. We build on recent deep learningmethods capable of generating a complete 3D reconstruction of an object from asingle image. Specifically, in this work, we extend a recent method which usesHigher Order Functions (HOF) to represent the shape of the object. We present anew generalization of this method to incorporate multiple images as input andestablish a connection between visibility and reconstruction quality. Thisrelationship forms the foundation of our view planning method where we computeviewpoints to visually cover the output of the multi-view HOF network with asfew images as possible. Experiments indicate that our method provides a goodcompromise between online and offline methods: Similar to online methods, ourmethod does not require the true object model as input. In terms of number ofviews, it is much more efficient. In most cases, its performance is comparableto the optimal offline case even on object classes the network has not beentrained on.

Higher Order Function Networks for View Planning and Multi-View Reconstruction