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

Segmentation of planar regions from a single RGB image is a particularlyimportant task in the perception of complex scenes. To utilize both visual andgeometric properties in images, recent approaches often formulate the problemas a joint estimation of planar instances and dense depth through featurefusion mechanisms and geometric constraint losses. Despite promising results,these methods do not consider cross-task feature distillation and performpoorly in boundary regions. To overcome these limitations, we propose X-PDNet,a framework for the multitask learning of plane instance segmentation and depthestimation with improvements in the following two aspects. Firstly, weconstruct the cross-task distillation design which promotes early informationsharing between dual-tasks for specific task improvements. Secondly, wehighlight the current limitations of using the ground truth boundary to developboundary regression loss, and propose a novel method that exploits depthinformation to support precise boundary region segmentation. Finally, wemanually annotate more than 3000 images from Stanford 2D-3D-Semantics datasetand make available for evaluation of plane instance segmentation. Through theexperiments, our proposed methods prove the advantages, outperforming thebaseline with large improvement margins in the quantitative results on theScanNet and the Stanford 2D-3D-S dataset, demonstrating the effectiveness ofour proposals.

X-PDNet: Accurate Joint Plane Instance Segmentation and Monocular Depth Estimation with Cross-Task Distillation and Boundary Correction