Loading…

Differentiable Deformation Graph-Based Neural Non-rigid Registration

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...

Full description

Saved in:
Bibliographic Details
Published in:Communications in mathematics and statistics 2023-03, Vol.11 (1), p.151-167
Main Authors: Feng, Wanquan, Cai, Hongrui, Hou, Junhui, Deng, Bailin, Zhang, Juyong
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2194-6701
2194-671X
DOI:10.1007/s40304-023-00341-x