Bidirectional Patch-Based Correlations With Local Rigidity for Global Nonrigid Registration
- 21 August 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (7) , 6740-6755
Abstract
The registration of time-varying 3D shapes with high degrees of freedom remains a challenging task. Most existing techniques attempt to address this issue by solving an optimization problem defined on deformation graph with as-rigid-as-possible smoothness prior, which usually struggle to capture large scale displacements. Motivated by the insight that a set of points tends to collectively undergo significant rigid motion accompanied by slight nonrigid deformation, we propose a two-step approach to address nonrigid registration in a coarse-to- fine manner. In the first step, coarse correlations between source and target points are constructed by estimating a set of rigid transformations for local patches which are regional clusters of points. To leverage more contextual information, a bidirectional registration module is introduced that estimates both the forward and backward patch-wise rigid transformation fields (PRTFs). Subsequently, in the second step, the source point set is warped by blending both forward and backward PRTFs and fed into a deformation optimization module. Here, unidirectional point-based correspondences are sought to refine the global nonrigid transformation fields (GNTFs) while adhering to local rigidity constraints. To illustrate the efficacy of our method, we conduct tests on challenging scenarios involving human datasets, including large displacements resulting from fast inter-frame motions or pose changes. Both qualitative and quantitative results demonstrate that our approach outperforms several state-of-the-art methods in terms of robustness and registration accuracy.Keywords
Funding Information
- National Key Research and Development Program of China (2018AAA0102801)
- National Natural Science Foundation of China (62131011)
This publication has 72 references indexed in Scilit:
- Arbitrary Order Total Variation for Deformable Image RegistrationPattern Recognition, 2023
- Nesterov Accelerated ADMM for Fast Diffeomorphic Image Registration2021
- 3D Face Hallucination from a Single Depth Frame2014
- Nonrigid Surface Registration and Completion from RGBD Images2014
- A Generative Model for the Joint Registration of Multiple Point Sets2014
- Free-form mesh tracking: A patch-based approach2010
- Piecewise Quadratic Reconstruction of Non-Rigid Surfaces from Monocular Sequences2010
- Unique Signatures of Histograms for Local Surface Description2010
- Optimal Step Nonrigid ICP Algorithms for Surface Registration2007
- Registering multiview range data to create 3D computer objectsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1995