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

This paper introduces SD-6DoF-ICLK, a learning-based Inverse CompositionalLucas-Kanade (ICLK) pipeline that uses sparse depth information to optimize therelative pose that best aligns two images on SE(3). To compute this sixDegrees-of-Freedom (DoF) relative transformation, the proposed formulationrequires only sparse depth information in one of the images, which is often theonly available depth source in visual-inertial odometry or SimultaneousLocalization and Mapping (SLAM) pipelines. In an optional subsequent step, theframework further refines feature locations and the relative pose usingindividual feature alignment and bundle adjustment for pose and structurere-alignment. The resulting sparse point correspondences with subpixel-accuracyand refined relative pose can be used for depth map generation, or the imagealignment module can be embedded in an odometry or mapping framework.Experiments with rendered imagery show that the forward SD-6DoF-ICLK runs at145 ms per image pair with a resolution of 752 x 480 pixels each, and vastlyoutperforms the classical, sparse 6DoF-ICLK algorithm, making it the idealframework for robust image alignment under severe conditions.

SD-6DoF-ICLK: Sparse and Deep Inverse Compositional Lucas-Kanade Algorithm on SE(3)