Filters








642 Hits in 3.0 sec

High Order Mesh Denoising via ℓp-ℓ1 Minimization

Zheng Liu, Mingqiang Guo, Zhong Xie, Jinqin Liu, Bohong Zeng
2019 IEEE Access  
INDEX TERMS Augmented lagrangian method, iteratively reweighted 1 minimization, mesh denoising, 3D geometry processing.  ...  We testify effectiveness of our mesh denoising method on synthetic meshes and a broad variety of scanning data produced by the laser scanner and Kinect sensors.  ...  In our opinion, mesh denoising methods can be rough classified into three categories: filter-based, optimization-based, and data-driven methods.  ... 
doi:10.1109/access.2019.2939362 fatcat:m4vdn5djdvbujgkddz3irvmfrm

DNF-Net: a Deep Normal Filtering Network for Mesh Denoising

Xianzhi Li, Ruihui Li, Lei Zhu, Chi-Wing Fu, Pheng-Ann Heng
2020 IEEE Transactions on Visualization and Computer Graphics  
Compared with the recent data-driven works on mesh denoising, DNF-Net does not require manual input to extract features and better utilizes the training data to enhance its denoising performance.  ...  To better capture local geometry, our network processes the mesh in terms of local patches extracted from the mesh.  ...  Data-driven methods for mesh denoising There have been increasing attention on exploiting datadriven methods to denoise meshes. Wang et al.  ... 
doi:10.1109/tvcg.2020.3001681 pmid:32746260 fatcat:w3y63aywnnh7jix7iu3kfhcdhe

Fast mesh denoising with data driven normal filtering using deep variational autoencoders

Stavros Nousias, Gerasimos Arvanitis, Aris Lalos, Konstantinos Moustakas
2020 IEEE Transactions on Industrial Informatics  
Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times.  ...  In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models.  ...  [16] suggested a data-driven method for mesh denoising that uses training sets of noisy objects.  ... 
doi:10.1109/tii.2020.3000491 fatcat:g2t5nlhegnexnepifvv46nfiee

GCN-Denoiser: Mesh Denoising with Graph Convolutional Networks [article]

Yuefan Shen, Hongbo Fu, Zhongshuo Du, Xiang Chen, Evgeny Burnaev, Denis Zorin, Kun Zhou, Youyi Zheng
2021 arXiv   pre-print
Our code and data are available in https://github.com/Jhonve/GCN-Denoiser.  ...  In this paper, we present GCN-Denoiser, a novel feature-preserving mesh denoising method based on graph convolutional networks (GCNs).  ...  Data-driven methods have attracted a lot of attention lately and several approaches have been introduced for mesh denoising [Li et al. 2020c; Wang et al. 2016; Zhao et al. 2019b ].  ... 
arXiv:2108.05128v1 fatcat:mq4nzoxrzzgs5ikvtmbl3zb53y

Fast Feature-Preserving Approach to Carpal Bone Surface Denoising

Ibrahim Salim, A. Hamza
2018 Sensors  
Both terms are weighted by a normalized mesh Laplacian, which is defined in terms of a data-adaptive kernel similarity matrix in conjunction with matrix balancing.  ...  We present a geometric framework for surface denoising using graph signal processing, which is an emerging field that aims to develop new tools for processing and analyzing graph-structured data.  ...  For the future work, we plan to incorporate edge-aware filters into our framework to tackle data-driven geometry processing problems.  ... 
doi:10.3390/s18072379 pmid:30037109 pmcid:PMC6069221 fatcat:lie73rd4rndztmvw73dkcmdvfu

A PDE patch-based spectral method for progressive mesh compression and mesh denoising

Qiqi Shen, Yun Sheng, Congkun Chen, Guixu Zhang, Hassan Ugail
2017 The Visual Computer  
In this paper we, for the first time, extend the use of the PDE method to progressive mesh compression and mesh denoising.  ...  Experimental results demonstrate the feasibility of our method in both progressive mesh compression and mesh denoising.  ...  All the above are of connectivity-driven algorithms that first encode connectivity data and then use them to encode geometry data. Instead, geometrydriven algorithms proceed in an opposite way.  ... 
doi:10.1007/s00371-017-1431-4 fatcat:vbv2eigmwnf43banegoydowah4

Spatially Adaptive Regularizer for Mesh Denoising

Xuan Cheng, Yinglin Zheng, Yuhui Zheng, Fang Chen, Kunhui Lin
2020 IEEE Access  
Mesh denoising is a fundamental yet not well-solved problem in computer graphics.  ...  INDEX TERMS L p norm, mesh denoising, optimization, regularizer, spatially adaptive.  ...  Liu for providing us the denoised results of TVNF [26] and ASONF [29] on the benchmark data.  ... 
doi:10.1109/access.2020.2987046 fatcat:erv6r2ly6jbg7pd53hijhtenoa

Fast mesh denoising with data driven normal filtering using deep variational autoencoders

Stavros Nousias, Gerasimos Arvanitis, Aris S. Lalos, Konstantinos Moustakas
2020 Zenodo  
Training and inference are performed in a sliding patch setup reducing the size of the required training data and execution times.  ...  In this work, we propose a fast and robust denoising method for dense 3D scanned industrial models.  ...  The authors in [16] suggest a data-driven method for mesh denoising that uses training sets of noisy objects.  ... 
doi:10.5281/zenodo.3865275 fatcat:p7dbz6ya2bc5hfgtywielvuipq

Mesh Total Generalized Variation for Denoising [article]

Zheng Liu, YanLei Li, Weina Wang, Ligang Liu, Renjie Chen
2021 arXiv   pre-print
Further, we propose a TGV-based variational model to restore the face normal field for mesh denoising.  ...  Extensive results and comparisons on synthetic and real scanning data validate that the proposed method outperforms the state-of-the-art methods visually and numerically.  ...  Data-driven methods. More recently, the data-driven methods have received increasing attention. Wang et al.  ... 
arXiv:2101.02322v2 fatcat:mi5nzytlcnh23pdnahwo2vfdo4

Segmentation Based Mesh Denoising [article]

Chaofan Dai, Wei Pan, Xuequan Lu
2020 arXiv   pre-print
Feature-preserving mesh denoising has received noticeable attention recently.  ...  In this paper, we propose a novel clustering method for mesh denoising, which can avoid the disturbance of anisotropic information and be easily embedded into commonly-used mesh denoising frameworks.  ...  Recent advances in deep learning lead to new data-driven methods for mesh segmentation [29] .  ... 
arXiv:2008.01358v2 fatcat:3co3bibmzrh2nmpkl3uvbbqeay

Modified Bilateral Filter for Feature Enhancement in Mesh Denoising

Hyeon-Deok Han, Jong-Ki Han
2022 IEEE Access  
INDEX TERMS Bilateral filter, feature enhancement, mesh denoising, mesh normal filtering.  ...  In this study, we design a feature enhancement filter that is combined with a conventional denoising filter to remove the noise while enhancing the features.  ...  Recently, various studies based on data-driven methods have also been conducted. A data-driven method was proposed by Diebel et al. [27] .  ... 
doi:10.1109/access.2022.3176961 fatcat:6i2pcfrgx5e6fo6ykeykawk4yy

Robust Mesh Denoising via Triple Sparsity

Saishang Zhong, Zhong Xie, Jinqin Liu, Zheng Liu
2019 Sensors  
Mesh denoising is to recover high quality meshes from noisy inputs scanned from the real world. It is a crucial step in geometry processing, computer vision, computer-aided design, etc.  ...  In this paper, we present a novel optimization method for robustly denoising the mesh.  ...  On the contrary, without any assumptions about the underlying surface, a data-driven method has been employed for mesh denoising [26] .  ... 
doi:10.3390/s19051001 fatcat:juhvapg6j5brdlmgbuvshqs3ca

Signal Processing on Static and Dynamic 3D Meshes: Sparse Representations and Applications

Aris S. Lalos, Evangelos Vlachos, Gerasimos Arvanitis, Konstantinos Moustakas, Kostas Berberidis
2019 IEEE Access  
INDEX TERMS Signal processing on static and dynamic meshes, sparse representation theory & algorithms, 3D geometry acquisition and processing.  ...  Moreover, the impact of sparse modeling and optimization tools to several 3D mesh processing tasks, such as completion of missing data, feature preserving noise removal, and rejection of outliers, is illustrated  ...  , and imposes lowrank to the recovered geometry, depending on the weighting parameter τ .  ... 
doi:10.1109/access.2019.2894533 fatcat:pistdxwe3zenrievtcktrco33i

NormalNet: Learning-based Normal Filtering for Mesh Denoising [article]

Wenbo Zhao, Xianming Liu, Yongsen Zhao, Xiaopeng Fan, Debin Zhao
2019 arXiv   pre-print
Mesh denoising is a critical technology in geometry processing that aims to recover high-fidelity 3D mesh models of objects from their noise-corrupted versions.  ...  The scheme follows the iterative framework of filtering-based mesh denoising.  ...  Hence, mesh denoising has become an active research topic in the area of geometry processing. Mesh denoising is an ill-posed inverse problem.  ... 
arXiv:1903.04015v2 fatcat:hnxzxubvhnfltlzssa7vjntqnq

Mesh Denoising Based on Recurrent Neural Networks

Yan Xing, Jieqing Tan, Peilin Hong, Yeyuan He, Min Hu
2022 Symmetry  
Inspired by these works, we propose a data-driven mesh denoising method based on recurrent neural networks, which learns the relationship between the feature descriptors and the ground-truth normals.  ...  Mesh denoising is a classical task in mesh processing.  ...  We would like to thank Peng-Shuai Wang for providing the data and codes for the mesh denoising.  ... 
doi:10.3390/sym14061233 fatcat:5enjbbwcrndpvdkwdslvm46way
« Previous Showing results 1 — 15 out of 642 results