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

Mobile AR applications benefit from fast initialization to displayworld-locked effects instantly. However, standard visual odometry or SLAMalgorithms require motion parallax to initialize (see Figure 1) and, therefore,suffer from delayed initialization. In this paper, we present a 6-DoF monocularvisual odometry that initializes instantly and without motion parallax. Ourmain contribution is a pose estimator that decouples estimating the 5-DoFrelative rotation and translation direction from the 1-DoF translationmagnitude. While scale is not observable in a monocular vision-only setting, itis still paramount to estimate a consistent scale over the whole trajectory(even if not physically accurate) to avoid AR effects moving erroneously alongdepth. In our approach, we leverage the fact that depth errors are notperceivable to the user during rotation-only motion. However, as the userstarts translating the device, depth becomes perceivable and so does thecapability to estimate consistent scale. Our proposed algorithm naturallytransitions between these two modes. We perform extensive validations of ourcontributions with both a publicly available dataset and synthetic data. Weshow that the proposed pose estimator outperforms the classical approaches for6-DoF pose estimation used in the literature in low-parallax configurations. Werelease a dataset for the relative pose problem using real data to facilitatethe comparison with future solutions for the relative pose problem. Oursolution is either used as a full odometry or as a preSLAM component of anysupported SLAM system (ARKit, ARCore) in world-locked AR effects on platformssuch as Instagram and Facebook.

Instant Visual Odometry Initialization for Mobile AR