DefTransNet: A Transformer-based Method for Non-Rigid Point Cloud Registration in the Simulation of Soft Tissue Deformation

2025-02-10

AI Summary

Non-rigid registration of soft-tissue point clouds remains challenging due to large deformations, sensor noise, partial overlap, and outliers—leading to poor robustness and low correspondence accuracy. To address this, we propose an end-to-end Transformer-based architecture that directly regresses a dense displacement field from source to target point clouds. Our key contributions are: (1) a learnable affine transformation module to improve initial alignment robustness; (2) a multi-scale geometric feature encoder that jointly captures global context and local structural details; and (3) a Transformer backbone to model long-range point-wise dependencies, thereby enhancing modeling capacity for complex, non-linear deformations. Extensive experiments on four benchmarks—ModelNet, SynBench, 4DMatch, and DeformedTissue—demonstrate consistent state-of-the-art performance, with significant gains in both registration accuracy and cross-domain generalization.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Soft-tissue surgeries, such as tumor resections, are complicated by tissue deformations that can obscure the accurate location and shape of tissues. By representing tissue surfaces as point clouds and applying non-rigid point cloud registration (PCR) methods, surgeons can better understand tissue deformations before, during, and after surgery. Existing non-rigid PCR methods, such as feature-based approaches, struggle with robustness against challenges like noise, outliers, partial data, and large deformations, making accurate point correspondence difficult. Although learning-based PCR methods, particularly Transformer-based approaches, have recently shown promise due to their attention mechanisms for capturing interactions, their robustness remains limited in challenging scenarios. In this paper, we present DefTransNet, a novel end-to-end Transformer-based architecture for non-rigid PCR. DefTransNet is designed to address the key challenges of deformable registration, including large deformations, outliers, noise, and partial data, by inputting source and target point clouds and outputting displacement vector fields. The proposed method incorporates a learnable transformation matrix to enhance robustness to affine transformations, integrates global and local geometric information, and captures long-range dependencies among points using Transformers. We validate our approach on four datasets: ModelNet, SynBench, 4DMatch, and DeformedTissue, using both synthetic and real-world data to demonstrate the generalization of our proposed method. Experimental results demonstrate that DefTransNet outperforms current state-of-the-art registration networks across various challenging conditions. Our code and data are publicly available.

Problem

• Handles non-rigid point cloud registration
• Addresses large deformations and outliers
• Improves robustness against noise and partial data

Innovation

• Transformer-based architecture
• Learnable transformation matrix
• Global and local geometric integration