A review of non-rigid transformations and learning-based 3D point cloud registration methods

Point cloud registration is a research field where the spatial relationship between two or more sets of points in space is determined. Point clouds are found in multiple applications, such as laser scanning, 3D reconstruction, and time-of-flight imaging, to mention a few. This paper provides a thorough overview of recent advances in learning-based 3D point cloud registration methods with an emphasis on non-rigid transformations. In this respect, the available studies should take various challenges like noise, outliers, different deformation levels, and data incompleteness into account. Therefore, a comparison study on the quantitative assessment metrics and robustness of different approaches is discussed. Furthermore, a comparative study on available datasets is reviewed. This information will help to understand the new range of possibilities and to inspire future research directions.