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

Estimating relative camera poses from consecutive frames is a fundamentalproblem in visual odometry (VO) and simultaneous localization and mapping(SLAM), where classic methods consisting of hand-crafted features andsampling-based outlier rejection have been a dominant choice for over a decade.Although multiple works propose to replace these modules with learning-basedcounterparts, most have not yet been as accurate, robust and generalizable asconventional methods. In this paper, we design an end-to-end trainableframework consisting of learnable modules for detection, feature extraction,matching and outlier rejection, while directly optimizing for the geometricpose objective. We show both quantitatively and qualitatively that poseestimation performance may be achieved on par with the classic pipeline.Moreover, we are able to show by end-to-end training, the key components of thepipeline could be significantly improved, which leads to bettergeneralizability to unseen datasets compared to existing learning-basedmethods.

Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints