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

Depth estimation and semantic segmentation play essential roles in sceneunderstanding. The state-of-the-art methods employ multi-task learning tosimultaneously learn models for these two tasks at the pixel-wise level. Theyusually focus on sharing the common features or stitching feature maps from thecorresponding branches. However, these methods lack in-depth consideration onthe correlation of the geometric cues and the scene parsing. In this paper, wefirst introduce the concept of semantic objectness to exploit the geometricrelationship of these two tasks through an analysis of the imaging process,then propose a Semantic Object Segmentation and Depth Estimation Network(SOSD-Net) based on the objectness assumption. To the best of our knowledge,SOSD-Net is the first network that exploits the geometry constraint forsimultaneous monocular depth estimation and semantic segmentation. In addition,considering the mutual implicit relationship between these two tasks, weexploit the iterative idea from the expectation-maximization algorithm to trainthe proposed network more effectively. Extensive experimental results on theCityscapes and NYU v2 dataset are presented to demonstrate the superiorperformance of the proposed approach.

SOSD-Net: Joint Semantic Object Segmentation and Depth Estimation from Monocular images