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 efficient algorithm to solve the multi-view registration problem,themotion averaging (MA) algorithm has been extensively studied and many MA-basedalgorithms have been introduced. They aim at recovering global motions fromrelative motions and exploiting information redundancy to average accumulativeerrors. However, one property of these methods is that they use Guass-Newtonmethod to solve a least squares problem for the increment of global motions,which may lead to low efficiency and poor robustness to outliers. In thispaper, we propose a novel motion averaging framework for the multi-viewregistration with Laplacian kernel-based maximum correntropy criterion (LMCC).Utilizing the Lie algebra motion framework and the correntropy measure, wepropose a new cost function that takes all constraints supplied by relativemotions into account. Obtaining the increment used to correct the globalmotions, can further be formulated as an optimization problem aimed atmaximizing the cost function. By virtue of the quadratic technique, theoptimization problem can be solved by dividing into two subproblems, i.e.,computing the weight for each relative motion according to the currentresiduals and solving a second-order cone program problem (SOCP) for theincrement in the next iteration. We also provide a novel strategy fordetermining the kernel width which ensures that our method can efficientlyexploit information redundancy supplied by relative motions in the presence ofmany outliers. Finally, we compare the proposed method with other MA-basedmulti-view registration methods to verify its performance. Experimental testson synthetic and real data demonstrate that our method achieves superiorperformance in terms of efficiency, accuracy and robustness.

Robust Motion Averaging for Multi-view Registration of Point Sets Based Maximum Correntropy Criterion