Cross-time registration of 3D point clouds

Abstract Registration is a ubiquitous operation in visual computing and constitutes an important pre-processing step for operations such as 3D object reconstruction, retrieval and recognition. Particularly in cultural heritage (CH) applications, registration techniques are essential for the digitization and restoration pipelines. Cross-time registration is a special case where the objects to be registered are instances of the same object after undergoing processes such as erosion or restoration. Traditional registration techniques are inadequate to address this problem with the required high accuracy for detecting minute changes; some are extremely slow. A deep learning registration framework for cross-time registration is proposed which uses the DeepGMR network in combination with a novel down-sampling scheme for cross-time registration. A dataset especially designed for cross-time registration is presented (called ECHO) and an extensive evaluation of state-of-the-art methods is conducted for the challenging case of cross-time registration.