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

Deep learning has shown to be effective for robust and real-time monocularimage relocalisation. In particular, PoseNet is a deep convolutional neuralnetwork which learns to regress the 6-DOF camera pose from a single image. Itlearns to localize using high level features and is robust to difficultlighting, motion blur and unknown camera intrinsics, where point based SIFTregistration fails. However, it was trained using a naive loss function, withhyper-parameters which require expensive tuning. In this paper, we give theproblem a more fundamental theoretical treatment. We explore a number of novelloss functions for learning camera pose which are based on geometry and scenereprojection error. Additionally we show how to automatically learn an optimalweighting to simultaneously regress position and orientation. By leveraginggeometry, we demonstrate that our technique significantly improves PoseNet'sperformance across datasets ranging from indoor rooms to a small city.

Geometric Loss Functions for Camera Pose Regression with Deep Learning