1
|
Liu Z, Zhao Y, Zhan S, Liu Y, Chen R, He Y. PCDNF: Revisiting Learning-Based Point Cloud Denoising via Joint Normal Filtering. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 2024; 30:5419-5436. [PMID: 37405886 DOI: 10.1109/tvcg.2023.3292464] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/07/2023]
Abstract
Point cloud denoising is a fundamental and challenging problem in geometry processing. Existing methods typically involve direct denoising of noisy input or filtering raw normals followed by point position updates. Recognizing the crucial relationship between point cloud denoising and normal filtering, we re-examine this problem from a multitask perspective and propose an end-to-end network called PCDNF for joint normal filtering-based point cloud denoising. We introduce an auxiliary normal filtering task to enhance the network's ability to remove noise while preserving geometric features more accurately. Our network incorporates two novel modules. First, we design a shape-aware selector to improve noise removal performance by constructing latent tangent space representations for specific points, taking into account learned point and normal features as well as geometric priors. Second, we develop a feature refinement module to fuse point and normal features, capitalizing on the strengths of point features in describing geometric details and normal features in representing geometric structures, such as sharp edges and corners. This combination overcomes the limitations of each feature type and better recovers geometric information. Extensive evaluations, comparisons, and ablation studies demonstrate that the proposed method outperforms state-of-the-art approaches in both point cloud denoising and normal filtering.
Collapse
|
2
|
Ho TT, Tran MT, Cui X, Lin CL, Baek S, Kim WJ, Lee CH, Jin GY, Chae KJ, Choi S. Human-airway surface mesh smoothing based on graph convolutional neural networks. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 246:108061. [PMID: 38341897 DOI: 10.1016/j.cmpb.2024.108061] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/22/2023] [Revised: 01/22/2024] [Accepted: 02/05/2024] [Indexed: 02/13/2024]
Abstract
BACKGROUND AND OBJECTIVE A detailed representation of the airway geometry in the respiratory system is critical for predicting precise airflow and pressure behaviors in computed tomography (CT)-image-based computational fluid dynamics (CFD). The CT-image-based geometry often contains artifacts, noise, and discontinuities due to the so-called stair step effect. Hence, an advanced surface smoothing is necessary. The existing smoothing methods based on the Laplacian operator drastically shrink airway geometries, resulting in the loss of information related to smaller branches. This study aims to introduce an unsupervised airway-mesh-smoothing learning (AMSL) method that preserves the original geometry of the three-dimensional (3D) airway for accurate CT-image-based CFD simulations. METHOD The AMSL method jointly trains two graph convolutional neural networks (GCNNs) defined on airway meshes to filter vertex positions and face normal vectors. In addition, it regularizes a combination of loss functions such as reproducibility, smoothness and consistency of vertex positions, and normal vectors. The AMSL adopts the concept of a deep mesh prior model, and it determines the self-similarity for mesh restoration without using a large dataset for training. Images of the airways of 20 subjects were smoothed by the AMSL method, and among them, the data of two subjects were used for the CFD simulations to assess the effect of airway smoothing on flow properties. RESULTS In 18 of 20 benchmark problems, the proposed smoothing method delivered better results compared with the conventional or state-of-the-art deep learning methods. Unlike the traditional smoothing, the AMSL successfully constructed 20 smoothed airways with airway diameters that were consistent with the original CT images. Besides, CFD simulations with the airways obtained by the AMSL method showed much smaller pressure drop and wall shear stress than the results obtained by the traditional method. CONCLUSIONS The airway model constructed by the AMSL method reproduces branch diameters accurately without any shrinkage, especially in the case of smaller airways. The accurate estimation of airway geometry using a smoothing method is critical for estimating flow properties in CFD simulations.
Collapse
Affiliation(s)
- Thao Thi Ho
- School of Mechanical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, South Korea
| | - Minh Tam Tran
- School of Mechanical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, South Korea
| | - Xinguang Cui
- School of Aerospace Engineering, Huazhong University of Science and Technology, Wuhan, China
| | - Ching-Long Lin
- Department of Mechanical Engineering, IIHR-Hydroscience and Engineering, University of Iowa, Iowa City, Iowa, USA
| | - Stephen Baek
- School of Data Science, University of Virginia, Charlottesville, VA, USA; Department of Mechanical and Aerospace Engineering, University of Virginia, Charlottesville, VA, USA
| | - Woo Jin Kim
- Department of Internal Medicine and Environmental Health Center, School of Medicine, Kangwon National University Hospital, Kangwon National University, Chuncheon, South Korea
| | - Chang Hyun Lee
- Department of Radiology, College of Medicine, Seoul National University, Seoul National University Hospital, Seoul, South Korea; Department of Radiology, College of Medicine, The University of Iowa, Iowa City, IA, USA
| | - Gong Yong Jin
- Department of Radiology, Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju, South Korea
| | - Kum Ju Chae
- Department of Radiology, Research Institute of Clinical Medicine of Jeonbuk National University-Biomedical Research Institute of Jeonbuk National University Hospital, Jeonju, South Korea
| | - Sanghun Choi
- School of Mechanical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 41566, South Korea.
| |
Collapse
|
3
|
Wu L, Hou Y, Xu J, Zhao Y. Robust Mesh Segmentation Using Feature-Aware Region Fusion. SENSORS (BASEL, SWITZERLAND) 2022; 23:416. [PMID: 36617011 PMCID: PMC9824490 DOI: 10.3390/s23010416] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/30/2022] [Revised: 12/19/2022] [Accepted: 12/28/2022] [Indexed: 06/17/2023]
Abstract
This paper introduces a simple but powerful segmentation algorithm for 3D meshes. Our algorithm consists of two stages: over-segmentation and region fusion. In the first stage, adaptive space partition is applied to perform over-segmentation, which is very efficient. In the second stage, we define a new intra-region difference, inter-region difference, and fusion condition with the help of various shape features and propose an iterative region fusion method. As the region fusion process is feature aware, our algorithm can deal with complex 3D meshes robustly. Massive qualitative and quantitative experiments also validate the advantages of the proposed algorithm.
Collapse
Affiliation(s)
- Lulu Wu
- School of Mathematical Sciences, Ocean University of China, Qingdao 266100, China
| | - Yu Hou
- School of Mathematical Sciences, Ocean University of China, Qingdao 266100, China
| | - Junli Xu
- School of Mathematics and Physics, Qingdao University of Science and Technology, Qingdao 266061, China
| | - Yong Zhao
- School of Mathematical Sciences, Ocean University of China, Qingdao 266100, China
| |
Collapse
|
4
|
Shen LY, Wang MX, Ma HY, Feng YF, Yuan CM. A framework from point clouds to workpieces. Vis Comput Ind Biomed Art 2022; 5:21. [PMID: 35995889 PMCID: PMC9395558 DOI: 10.1186/s42492-022-00117-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/01/2022] [Accepted: 08/08/2022] [Indexed: 11/10/2022] Open
Abstract
Combining computer-aided design and computer numerical control (CNC) with global technical connections have become interesting topics in the manufacturing industry. A framework was implemented that includes point clouds to workpieces and consists of a mesh generation from geometric data, optimal surface segmentation for CNC, and tool path planning with a certified scallop height. The latest methods were introduced into the mesh generation with implicit geometric regularization and total generalized variation. Once the mesh model was obtained, a fast and robust optimal surface segmentation method is provided by establishing a weighted graph and searching for the minimum spanning tree of the graph for extraordinary points. This method is easy to implement, and the number of segmented patches can be controlled while preserving the sharp features of the workpiece. Finally, a contour parallel tool-path with a confined scallop height is generated on each patch based on B-spline fitting. Experimental results show that the proposed framework is effective and robust.
Collapse
|
5
|
A Robust Rigid Registration Framework of 3D Indoor Scene Point Clouds Based on RGB-D Information. REMOTE SENSING 2021. [DOI: 10.3390/rs13234755] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Rigid registration of 3D indoor scenes is a fundamental yet vital task in various fields that include remote sensing (e.g., 3D reconstruction of indoor scenes), photogrammetry measurement, geometry modeling, etc. Nevertheless, state-of-the-art registration approaches still have defects when dealing with low-quality indoor scene point clouds derived from consumer-grade RGB-D sensors. The major challenge is accurately extracting correspondences between a pair of low-quality point clouds when they contain considerable noise, outliers, or weak texture features. To solve the problem, we present a point cloud registration framework in view of RGB-D information. First, we propose a point normal filter for effectively removing noise and simultaneously maintaining sharp geometric features and smooth transition regions. Second, we design a correspondence extraction scheme based on a novel descriptor encoding textural and geometry information, which can robustly establish dense correspondences between a pair of low-quality point clouds. Finally, we propose a point-to-plane registration technology via a nonconvex regularizer, which can further diminish the influence of those false correspondences and produce an exact rigid transformation between a pair of point clouds. Compared to existing state-of-the-art techniques, intensive experimental results demonstrate that our registration framework is excellent visually and numerically, especially for dealing with low-quality indoor scenes.
Collapse
|