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

The task of predicting smooth and edge-consistent depth maps is notoriouslydifficult for single image depth estimation. This paper proposes a novelBilateral Grid based 3D convolutional neural network, dubbed as 3DBG-UNet, thatparameterizes high dimensional feature space by encoding compact 3D bilateralgrids with UNets and infers sharp geometric layout of the scene. Further,another novel 3DBGES-UNet model is introduced that integrate 3DBG-UNet forinferring an accurate depth map given a single color view. The 3DBGES-UNetconcatenates 3DBG-UNet geometry map with the inception network edgeaccentuation map and a spatial object's boundary map obtained by leveragingsemantic segmentation and train the UNet model with ResNet backbone. Bothmodels are designed with a particular attention to explicitly account for edgesor minute details. Preserving sharp discontinuities at depth edges is criticalfor many applications such as realistic integration of virtual objects in ARvideo or occlusion-aware view synthesis for 3D display applications.Theproposed depth prediction network achieves state-of-the-art performance in bothqualitative and quantitative evaluations on the challenging NYUv2-Depth data.The code and corresponding pre-trained weights will be made publicly available.

A Novel 3D-UNet Deep Learning Framework Based on High-Dimensional Bilateral Grid for Edge Consistent Single Image Depth Estimation