Graph-Based Feature-Preserving Mesh Normal Filtering

Zhao, Wenbo; Liu, Xianming; Wang, Shiqi; Fan, Xiaopeng; Zhao, Debin

doi:10.1109/tvcg.2019.2944357

Cited by 20 publications

(28 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in [34] introduced a two-stage scheme to construct adaptive consistent neighborhoods for guided normal filtering. The authors in [2] proposed further choosing a more consistent sub-patch to estimate the guidance normal. The authors in [35] developed a novel patch normal co-filtering method from the nonlocal similarity prior, the guidance normal obtained from the low-rank matrix recovery.…”

Section: Anisotropic Mesh Filteringmentioning

confidence: 99%

“…Feature-based methods. Common methods for feature recognition or the extraction of meshes represented by vertices, edges and faces include curvature-based methods [40,41], methods based on topological connections or geometric features [2], learning-based methods [42] and methods based on normal tensor voting [43,44]. The method based on the NVT easily classifies edge feature points and corner feature points, and it has been widely used in mesh denoising technology.…”

Section: Anisotropic Mesh Filteringmentioning

confidence: 99%

“…3D mesh denoising seeks to eliminate the noise on the surface, which has recently become a major focus of 3D mesh pre-processing method research. The challenging nature of mesh denoising is recovering the structural features of the surface without introducing false features into the smooth area when evolving a noisy mesh to its unknown noise-free counterpart [2]. Many mesh denoising attempts directly filter vertex positions [3] or facet normals followed by updating vertex positions [4].…”

Section: Introductionmentioning

confidence: 99%

“…Many mesh denoising attempts directly filter vertex positions [3] or facet normals followed by updating vertex positions [4]. However, vertex positions and surface normals are both sensitive to noise, and they even become unreliable when the noise level increases in denoising [2]. Recently, the GMNF method [5] was proposed to overcome the noise sensitivity of facet normals.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

3D Mesh Pre-Processing Method Based on Feature Point Classification and Anisotropic Vertex Denoising Considering Scene Structure Characteristics

et al. 2021

View full text Add to dashboard Cite

3D mesh denoising plays an important role in 3D model pre-processing and repair. A fundamental challenge in the mesh denoising process is to accurately extract features from the noise and to preserve and restore the scene structure features of the model. In this paper, we propose a novel feature-preserving mesh denoising method, which was based on robust guidance normal estimation, accurate feature point extraction and an anisotropic vertex denoising strategy. The methodology of the proposed approach is as follows: (1) The dual weight function that takes into account the angle characteristics is used to estimate the guidance normals of the surface, which improved the reliability of the joint bilateral filtering algorithm and avoids losing the corner structures; (2) The filtered facet normal is used to classify the feature points based on the normal voting tensor (NVT) method, which raised the accuracy and integrity of feature classification for the noisy model; (3) The anisotropic vertex update strategy is used in triangular mesh denoising: updating the non-feature points with isotropic neighborhood normals, which effectively suppressed the sharp edges from being smoothed; updating the feature points based on local geometric constraints, which preserved and restored the features while avoided sharp pseudo features. The detailed quantitative and qualitative analyses conducted on synthetic and real data show that our method can remove the noise of various mesh models and retain or restore the edge and corner features of the model without generating pseudo features.

show abstract

Section: Anisotropic Mesh Filteringmentioning

confidence: 99%

Section: Anisotropic Mesh Filteringmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

3D Mesh Pre-Processing Method Based on Feature Point Classification and Anisotropic Vertex Denoising Considering Scene Structure Characteristics

et al. 2021

View full text Add to dashboard Cite

show abstract

“…F EATURE preserving 3D model denoising plays an essential role in preprocessing of point clouds [1], [2] or triangular meshes [3]- [10] , which are obtained by scanning devices or via various kinds of digitalization processes. Previous methods can be roughly divided into four categories, namely, local methods, global methods, multi-step and deep learning based methods.…”

Section: Introductionmentioning

confidence: 99%

Adaptive and Feature-Preserving Mesh Denoising Schemes Based on Developmental Guidance

Yue

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Distinguishing among different kinds of features as well as noises on 3D mesh models is crucial for feature-preserving mesh denoising. This paper proposes to address this issue via in-depth analysis of the intermediate products of the denoising processes, and one framework is presented for raising adaptive and feature-preserving mesh denoising schemes. Firstly, by analyzing the changes of the facet normals during the denoising process, we propose the definition of developmental guidance, which helps to assess the current filtering status and predict the positions of feature and smooth regions. Then, by incorporating the guidance, we put forward one interpolation-based denoising scheme, which affords an efficient way to interpolate and recover different levels of features and is robust to severe noises. Besides, we also introduce the guidance to the optimization-based model, and the achieved global scheme is tested to be stable and robust to irregular samplings. Both the theoretical analysis and extensive experimental results on synthetic and real-world noises have demonstrated the attractive advantages of our whole framework, such as being adaptive, efficient, robust, feature-preserving, etc. INDEX TERMS bilateral filtering, feature-preserving, guided filter, linear interpolation, mesh denoising

show abstract

Learning Self-prior for Mesh Denoising Using Dual Graph Convolutional Networks

Hattori

Yatagawa

Ohtake

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This study presents a self-prior-based mesh inpainting framework that requires only an incomplete mesh as input, without the need for any training datasets. Additionally, our method maintains the polygonal mesh format throughout the inpainting process without converting the shape format to an intermediate, such as a voxel grid, a point cloud, or an implicit function, which are typically considered easier for deep neural networks to process. To achieve this goal, we introduce two graph convolutional networks (GCNs): single-resolution GCN (SGCN) and multi-resolution GCN (MGCN), both trained in a self-supervised manner. Our approach refines a watertight mesh obtained from the initial hole filling to generate a completed output mesh. Specifically, we train the GCNs to deform an oversmoothed version of the input mesh into the expected completed shape. To supervise the GCNs for accurate vertex displacements, despite the unknown correct displacements at real holes, we utilize multiple sets of meshes with several connected regions marked as fake holes. The correct displacements are known for vertices in these fake holes, enabling network training with loss functions that assess the accuracy of displacement vectors estimated by the GCNs. We demonstrate that our method outperforms traditional dataset-independent approaches and exhibits greater robustness compared to other deep-learning-based methods for shapes that less frequently appear in shape datasets.

show abstract

Graph-Based Feature-Preserving Mesh Normal Filtering

Cited by 20 publications

References 41 publications

3D Mesh Pre-Processing Method Based on Feature Point Classification and Anisotropic Vertex Denoising Considering Scene Structure Characteristics

3D Mesh Pre-Processing Method Based on Feature Point Classification and Anisotropic Vertex Denoising Considering Scene Structure Characteristics

Adaptive and Feature-Preserving Mesh Denoising Schemes Based on Developmental Guidance

Learning Self-prior for Mesh Denoising Using Dual Graph Convolutional Networks

Contact Info

Product

Resources

About