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 focus on enabling damage and tampering detection in logistics and tacklethe problem of 3D shape reconstruction of potentially damaged parcels. As inputwe utilize single RGB images, which corresponds to use-cases where only simplehandheld devices are available, e.g. for postmen during delivery or clients ondelivery. We present a novel synthetic dataset, named Parcel3D, that is basedon the Google Scanned Objects (GSO) dataset and consists of more than 13,000images of parcels with full 3D annotations. The dataset contains intact, i.e.cuboid-shaped, parcels and damaged parcels, which were generated insimulations. We work towards detecting mishandling of parcels by presenting anovel architecture called CubeRefine R-CNN, which combines estimating a 3Dbounding box with an iterative mesh refinement. We benchmark our approach onParcel3D and an existing dataset of cuboid-shaped parcels in real-worldscenarios. Our results show, that while training on Parcel3D enables transferto the real world, enabling reliable deployment in real-world scenarios isstill challenging. CubeRefine R-CNN yields competitive performance in terms ofMesh AP and is the only model that directly enables deformation assessment by3D mesh comparison and tampering detection by comparing viewpoint invariantparcel side surface representations. Dataset and code are available athttps://a-nau.github.io/parcel3d.

Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logistics