资源论文Gravitational Approach for Point Set Registration

Gravitational Approach for Point Set Registration

2019-12-20 | |  57 |   45 |   0

Abstract

In this paper a new astrodynamics inspired rigid pointset registration algorithm is introduced — the GravitationalApproach (GA). We formulate point set registration as amodified N -body problem with additional constraints andobtain an algorithm with unique properties which is fullyscalable with the number of processing cores. In GA, a tem-plate point set moves in a viscous medium under gravita-tional forces induced by a reference point set. Pose updates are completed by numerically solving the differential equations of Newtonian mechanics. We discuss techniques for efficient implementation of the new algorithm and evaluate it on several synthetic and real-world scenarios. GA is compared with the widely used Iterative Closest Point and thestate of the art rigid Coherent Point Drift algorithms. Ex-periments evidence that the new approach is robust againstnoise and can handle challenging scenarios with structuredoutliers.

上一篇:Synthesized Classifiers for Zero-Shot Learning

下一篇:An Empirical Evaluation of Current Convolutional Architectures’ Ability to Manage Nuisance Location and Scale Variability

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...