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

Piece-wise 3D planar reconstruction provides holistic scene understanding ofman-made environments, especially for indoor scenarios. Most recent approachesfocused on improving the segmentation and reconstruction results by introducingadvanced network architectures but overlooked the dual characteristics ofpiece-wise planes as objects and geometric models. Different from otherexisting approaches, we start from enforcing cross-task consistency for ourmulti-task convolutional neural network, PlaneRecNet, which integrates asingle-stage instance segmentation network for piece-wise planar segmentationand a depth decoder to reconstruct the scene from a single RGB image. Toachieve this, we introduce several novel loss functions (geometric constraint)that jointly improve the accuracy of piece-wise planar segmentation and depthestimation. Meanwhile, a novel Plane Prior Attention module is used to guidedepth estimation with the awareness of plane instances. Exhaustive experimentsare conducted in this work to validate the effectiveness and efficiency of ourmethod.

PlaneRecNet: Multi-Task Learning with Cross-Task Consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image