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

As an essential part of structure from motion (SfM) and SimultaneousLocalization and Mapping (SLAM) systems, motion averaging has been extensivelystudied in the past years and continues to attract surging research attention.While canonical approaches such as bundle adjustment are predominantlyinherited in most of state-of-the-art SLAM systems to estimate and update thetrajectory in the robot navigation, the practical implementation of bundleadjustment in SLAM systems is intrinsically limited by the high computationalcomplexity, unreliable convergence and strict requirements of idealinitializations. In this paper, we lift these limitations and propose a noveloptimization backbone for visual SLAM systems, where we leverage rotationaveraging to improve the accuracy, efficiency and robustness of conventionalmonocular SLAM pipelines. In our approach, we first decouple the rotational andtranslational parameters in the camera rigid body transformation and convertthe high-dimensional non-convex nonlinear problem into tractable linearsubproblems in lower dimensions, and show that the subproblems can be solvedindependently with proper constraints. We apply the scale parameter with$l_1$-norm in the pose-graph optimization to address the rotation averagingrobustness against outliers. We further validate the global optimality of ourproposed approach, revisit and address the initialization schemes, purerotational scene handling and outlier treatments. We demonstrate that ourapproach can exhibit up to 10x faster speed with comparable accuracy againstthe state of the art on public benchmarks.

Pushing the Envelope of Rotation Averaging for Visual SLAM