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

Instance segmentation of planar regions in indoor scenes benefits visual SLAMand other applications such as augmented reality (AR) where scene understandingis required. Existing methods built upon two-stage frameworks show satisfactoryaccuracy but are limited by low frame rates. In this work, we propose areal-time deep neural architecture that estimates piece-wise planar regionsfrom a single RGB image. Our model employs a variant of a fast single-stage CNNarchitecture to segment plane instances. Considering the particularity of thetarget detected, we propose Fast Feature Non-maximum Suppression (FF-NMS) toreduce the suppression errors resulted from overlapping bounding boxes ofplanes. We also utilize a Residual Feature Augmentation module in the FeaturePyramid Network (FPN). Our method achieves significantly higher frame-rates andcomparable segmentation accuracy against two-stage methods. We automaticallylabel over 70,000 images as ground truth from the Stanford 2D-3D-Semanticsdataset. Moreover, we incorporate our method with a state-of-the-art planarSLAM and validate its benefits.

PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN