[HTML][HTML] A review of medical image registration for different modalities

F Darzi, T Bocklitz - Bioengineering, 2024 - mdpi.com
Medical image registration has become pivotal in recent years with the integration of various
imaging modalities like X-ray, ultrasound, MRI, and CT scans, enabling comprehensive …

CMDGAT: Knowledge extraction and retention based continual graph attention network for point cloud registration

A Zaman, F Yangyu, MS Ayub, M Irfan, L Guoyun… - Expert Systems with …, 2023 - Elsevier
Artificial Intelligence-based systems are required to interact with dynamic environments to
continuously learn, retain and effectively utilize knowledge. Present AI-based systems …

RoCNet++: Triangle-based descriptor for accurate and robust point cloud registration

K Slimani, C Achard, B Tamadazte - Pattern Recognition, 2024 - Elsevier
This paper introduces RoCNet++, a point cloud registration method with two main
contributions, one concerning the design of a robust descriptor and another concerning the …

On the pros and cons of momentum encoder in self-supervised visual representation learning

T Pham, C Zhang, A Niu, K Zhang, CD Yoo - ar** using low-cost MLS point clouds and architectural skeleton constraints
J Luo, Q Ye, S Zhang, Z Yang - Automation in Construction, 2023 - Elsevier
Abstract MLS (Mobile Laser Scanner) offers adequate mobility and the ability to obtain
accurate environmental data. However, it still faces some challenges, such as the heavy …

Hybrid optimization with unconstrained variables on partial point cloud registration

Y Yan, J An, J Zhao, F Shen - Pattern Recognition, 2023 - Elsevier
Abstract 3D point cloud registration is a fundamental problem in computer vision (CV) and
computer graphics (CG). Recently, a series of learning-based algorithms have been …

LPCL: Localized prominence contrastive learning for self-supervised dense visual pre-training

Z Chen, H Zhu, H Cheng, S Mi, Y Zhang, X Geng - Pattern Recognition, 2023 - Elsevier
Self-supervised pre-training has attracted increasing attention given its promising
performance in training backbone networks without using labels. By far, most methods focus …

Learning a task-specific descriptor for robust matching of 3D point clouds

Z Zhang, Y Dai, B Fan, J Sun… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Existing learning-based point feature descriptors are usually task-agnostic, which pursue
describing the individual 3D point clouds as accurate as possible. However, the matching …

Wasserstein distributional harvesting for highly dense 3D point clouds

DW Shu, SW Park, J Kwon - Pattern Recognition, 2022 - Elsevier
In this paper, we present a novel 3D point cloud harvesting method, which can harvest 3D
points from an estimated surface distribution in an unsupervised manner (ie, an input is a …