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 a new algorithm for multi-region segmentation of 2D images withobjects that may partially occlude each other. Our algorithm is based on theobservation hat human performance on this task is based both on prior knowledgeabout plausible shapes and taking into account the presence of occludingobjects whose shape is already known - once an occluded region is identified,the shape prior can be used to guess the shape of the missing part. We capturethe former aspect using a deep learning model of shape; for the latter, wesimultaneously minimize the energy of all regions and consider only unoccludedpixels for data agreement.  Existing algorithms incorporating object shape priors consider every objectseparately in turn and can't distinguish genuine deviation from the expectedshape from parts missing due to occlusion. We show that our methodsignificantly improves on the performance of a representative algorithm, asevaluated on both preprocessed natural and synthetic images. Furthermore, onthe synthetic images, we recover the ground truth segmentation with goodaccuracy.

In the Shadows, Shape Priors Shine: Using Occlusion to Improve Multi-Region Segmentation