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 novel method to estimate the motion matrix between overlappingpairs of 3D views in the context of indoor scenes. We use the Manhattan worldassumption to introduce lightweight geometric constraints under the form ofplanes into the problem, which reduces complexity by taking into account thestructure of the scene. In particular, we define a stochastic framework tocategorize planes as vertical or horizontal and parallel or non-parallel. Weleverage this classification to match pairs of planes in overlapping views withpoint-of-view agnostic structural metrics. We propose to split the motioncomputation using the classification and estimate separately the rotation andtranslation of the sensor, using a quadric minimizer. We validate our approachon a toy example and present quantitative experiments on a public RGB-Ddataset, comparing against recent state-of-the-art methods. Our evaluationshows that planar constraints only add low computational overhead whileimproving results in precision when applied after a prior coarse estimate. Weconclude by giving hints towards extensions and improvements of currentresults.

Plane Pair Matching for Efficient 3D View Registration