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

Omnidirectional 3D information is essential for a wide range of applicationssuch as Virtual Reality, Autonomous Driving, Robotics, etc. In this paper, wepropose a novel, model-agnostic, two-stage pipeline for omnidirectionalmonocular depth estimation. Our proposed framework PanoDepth takes one 360image as input, produces one or more synthesized views in the first stage, andfeeds the original image and the synthesized images into the subsequent stereomatching stage. In the second stage, we propose a differentiable SphericalWarping Layer to handle omnidirectional stereo geometry efficiently andeffectively. By utilizing the explicit stereo-based geometric constraints inthe stereo matching stage, PanoDepth can generate dense high-quality depth. Weconducted extensive experiments and ablation studies to evaluate PanoDepth withboth the full pipeline as well as the individual modules in each stage. Ourresults show that PanoDepth outperforms the state-of-the-art approaches by alarge margin for 360 monocular depth estimation.

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation