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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Object classification with 3D data is an essential component of any sceneunderstanding method. It has gained significant interest in a variety ofcommunities, most notably in robotics and computer graphics. While the adventof deep learning has progressed the field of 3D object classification, mostwork using this data type are solely evaluated on CAD model datasets.Consequently, current work does not address the discrepancies existing betweenreal and artificial data. In this work, we examine this gap in a roboticcontext by specifically addressing the problem of classification whentransferring from artificial CAD models to real reconstructed objects. This isperformed by training on ModelNet (CAD models) and evaluating on ScanNet(reconstructed objects). We show that standard methods do not perform well inthis task. We thus introduce a method that carefully samples object parts thatare reproducible under various transformations and hence robust. Using graphconvolution to classify the composed graph of parts, our method significantlyimproves upon the baseline.

Addressing the Sim2Real Gap in Robotic 3D Object Classification