Feng, Wanquan, Cai, Hongrui, Hou, Junhui, Deng, Bailin ORCID: https://orcid.org/0000-0002-0158-7670 and Zhang, Juyong 2023. Differentiable deformation graph-based neural non-rigid registration. Communications in Mathematics and Statistics 11 , pp. 151-167. 10.1007/s40304-023-00341-x |
Preview |
PDF
- Accepted Post-Print Version
Download (3MB) | Preview |
Abstract
The traditional pipeline for non-rigid registration is to iteratively update the correspondence and alignment such that the transformed source surface aligns well with the target surface. Among the pipeline, the correspondence construction and iterative manner are key to the results, while existing strategies might result in local optima. In this paper, we adopt the widely used deformation graph-based representation, while replacing some key modules with neural learning-based strategies. Specifically, we design a neural network to predict the correspondence and its reliability confidence rather than the strategies like nearest neighbor search and pair rejection. Besides, we adopt the GRU-based recurrent network for iterative refinement, which is more robust than the traditional strategy. The model is trained in a self-supervised manner and thus can be used for arbitrary datasets without ground-truth. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art methods by a large margin.
Item Type: | Article |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Computer Science & Informatics |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
Publisher: | Springer |
ISSN: | 2194-6701 |
Date of First Compliant Deposit: | 5 March 2023 |
Date of Acceptance: | 3 February 2023 |
Last Modified: | 28 Feb 2024 16:42 |
URI: | https://orca.cardiff.ac.uk/id/eprint/157501 |
Actions (repository staff only)
Edit Item |