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

3D semantic scene completion and 2D semantic segmentation are two tightlycorrelated tasks that are both essential for indoor scene understanding,because they predict the same semantic classes, using positively correlatedhigh-level features. Current methods use 2D features extracted from early-fusedRGB-D images for 2D segmentation to improve 3D scene completion. We argue thatthis sequential scheme does not ensure these two tasks fully benefit eachother, and present an Iterative Mutual Enhancement Network (IMENet) to solvethem jointly, which interactively refines the two tasks at the late predictionstage. Specifically, two refinement modules are developed under a unifiedframework for the two tasks. The first is a 2D Deformable Context Pyramid (DCP)module, which receives the projection from the current 3D predictions to refinethe 2D predictions. In turn, a 3D Deformable Depth Attention (DDA) module isproposed to leverage the reprojected results from 2D predictions to update thecoarse 3D predictions. This iterative fusion happens to the stable high-levelfeatures of both tasks at a late stage. Extensive experiments on NYU and NYUCADdatasets verify the effectiveness of the proposed iterative late fusion scheme,and our approach outperforms the state of the art on both 3D semantic scenecompletion and 2D semantic segmentation.

IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement