A family of globally optimal branch-and-bound algorithms for 2D–3D correspondence-free registration
作者：
Highlights：
• First globally optimal solution to the correspondence-free 2D-3D registration problem.
• The proposed branch-and-bound formulation provides intrinsic guarantees on optimality.
• Scene primitives invariance allowing registration from both point and line features.
• Deterministic and probabilistic procedures are introduced to speed-up convergence.
• The approach enables a significant increase in accuracy and robustness to outliers.
摘要
•First globally optimal solution to the correspondence-free 2D-3D registration problem.•The proposed branch-and-bound formulation provides intrinsic guarantees on optimality.•Scene primitives invariance allowing registration from both point and line features.•Deterministic and probabilistic procedures are introduced to speed-up convergence.•The approach enables a significant increase in accuracy and robustness to outliers.
论文关键词：2D–3D registration,Multi-modal registration,Branch-and-bound,Global optimisation
论文评审过程：Received 17 August 2018, Revised 15 February 2019, Accepted 4 April 2019, Available online 4 April 2019, Version of Record 16 April 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.002
