A Survey of Non-Rigid 3D Registration

TL;DR

This survey comprehensively reviews non-rigid 3D registration techniques, focusing on dynamic shape acquisition, deformation representation, and evaluation benchmarks, highlighting recent advances and future research directions.

Contribution

It provides a detailed overview of both optimization-based and learning-based non-rigid registration methods, including datasets and evaluation benchmarks, which was lacking in prior surveys.

Findings

Diverse deformation representation techniques are analyzed.

Both optimization and learning-based methods are compared.

Benchmark datasets for evaluation are summarized.

Abstract

Non-rigid registration computes an alignment between a source surface with a target surface in a non-rigid manner. In the past decade, with the advances in 3D sensing technologies that can measure time-varying surfaces, non-rigid registration has been applied for the acquisition of deformable shapes and has a wide range of applications. This survey presents a comprehensive review of non-rigid registration methods for 3D shapes, focusing on techniques related to dynamic shape acquisition and reconstruction. In particular, we review different approaches for representing the deformation field, and the methods for computing the desired deformation. Both optimization-based and learning-based methods are covered. We also review benchmarks and datasets for evaluating non-rigid registration methods, and discuss potential future research directions.