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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Depth map estimation from images is an important task in robotic systems.Existing methods can be categorized into two groups including multi-view stereoand monocular depth estimation. The former requires cameras to have largeoverlapping areas and sufficient baseline between cameras, while the latterthat processes each image independently can hardly guarantee the structureconsistency between cameras. In this paper, we propose a novel multi-cameracollaborative depth prediction method that does not require large overlappingareas while maintaining structure consistency between cameras. Specifically, weformulate the depth estimation as a weighted combination of depth basis, inwhich the weights are updated iteratively by a refinement network driven by theproposed consistency loss. During the iterative update, the results of depthestimation are compared across cameras and the information of overlapping areasis propagated to the whole depth maps with the help of basis formulation.Experimental results on DDAD and NuScenes datasets demonstrate the superiorperformance of our method.

Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation