Filters








133 Hits in 4.7 sec

Mesh Denoising Based on Normal Voting Tensor and Binary Optimization

Sunil Kumar Yadav, Ulrich Reitebuch, Konrad Polthier
2018 IEEE Transactions on Visualization and Computer Graphics  
Unlike other traditional averaging approaches, our approach uses an element based normal voting tensor to compute smooth surfaces.  ...  By introducing a binary optimization on the proposed tensor together with a local binary neighborhood concept, our algorithm better retains sharp features and produces smoother umbilical regions than previous  ...  We define an element based normal voting tensor on every element of a properly oriented triangulated mesh similar to the vertex based voting tensor proposed in [29] .  ... 
doi:10.1109/tvcg.2017.2740384 pmid:28829310 fatcat:itn4s5w54jfw7pcxclidq4sxka

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

Yawen Liu, Bingxuan Guo, Xiongwu Xiao, Wei Qiu
2021 Remote Sensing  
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  ...  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  ...  In general, we propose a 3D mesh Pre-processing method based on feature point classification and anisotropic vertex denoising considering the scene structure characteristics.  ... 
doi:10.3390/rs13112145 fatcat:6fuoawojtzacxbvpubkmul4ks4

Feature-Aware Trilateral Filter with Energy Minimization for 3D Mesh Denoising

Ye Wang, You Yang, Qiong Liu
2020 IEEE Access  
With the help of the model and filter, more priors are involved, and we can make global optimization for better denoising performance.  ...  A challenge arises on how to handle both surfaces and features simultaneously in 3D mesh denoising. Classical works mainly focused on surfaces, whereas features also reasonably need proper processes.  ...  In this step, the vertex-based normal voting tensor proposed in [34] is adopted for this purpose.  ... 
doi:10.1109/access.2020.2981161 fatcat:of2c5wcc4fcnfcdlw6m7gdzqe4

Adaptive and Feature-Preserving Bilateral Filters for Three-Dimensional Models

Nannan Li, Shaoyang Yue, Bo Jiang
2020 Traitement du signal  
during denoising, was designed based on the adaptive scale parameters.  ...  Bilateral filtering is a well-known tool to denoise or smooth one-dimensional (1D) signals, two-dimensional (2D) images, and three-dimensional (3D) models.  ...  One of the most popular ways to identify noises and features of mesh models is feature detection based on tensor voting. Wei et al.  ... 
doi:10.18280/ts.370202 fatcat:dhdxosmktnbsnnptgrroc3nvr4

Adaptive and Feature-preserving Mesh Denoising Schemes based on Developmental Guidance

Nannan Li, Shaoyang Yue, Zhiyang Li, Shengfa Wang, Hui Wang
2020 IEEE Access  
Distinguishing among different kinds of features as well as noises on 3D mesh models is crucial for feature-preserving mesh denoising.  ...  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.  ...  Feature detection methods based on tensor voting are widely used to identify noises and features of the mesh. Wei et al.  ... 
doi:10.1109/access.2020.3025227 fatcat:cswwtscs2vcfxcotqvg67a3zom

Robust and High Fidelity Mesh Denoising [article]

Sunil Kumar Yadav, Ulrich Reitebuch, Konrad Polthier
2017 arXiv   pre-print
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, the face normal filtering is done by using the bilateral normal filtering in the robust statistics  ...  This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.  ...  [20] proposed a guided mesh normal filtering based on the joint bilateral filtering [21] . A tensor voting guided mesh denoising was also introduced by Wei et al.  ... 
arXiv:1711.05341v2 fatcat:72bnp6dekvernpdmud4ravzmnu

Robust and High Fidelity Mesh Denoising

Sunil Kumar Yadav, Ulrich Reitebuch, Konrad Polthier
2018 IEEE Transactions on Visualization and Computer Graphics  
This paper presents a simple and effective two-stage mesh denoising algorithm, where in the first stage, the face normal filtering is done by using the bilateral normal filtering in the robust statistics  ...  This differential coordinate helps the algorithm to produce a high-quality mesh without any face normal flips and makes the method robust against high-intensity noise.  ...  [21] proposed a guided mesh normal filtering based on the joint bilateral filtering [22] . A tensor voting guided mesh denoising was also introduced by Wei et al.  ... 
doi:10.1109/tvcg.2018.2828818 pmid:29993913 fatcat:hzhuvostl5gyzojn5spuytfnlu

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.  ...  Results from experiments on synthetic and natural scanned models validate that the proposed method can restore false features by integrating conventional filtering-based methods, and outperforms other  ...  In this algorithm, mesh denoising is performed using binary optimization on the eigenvalues of the ENVT. In the non-local similarity method, Wei et al. [35] and Li et al.  ... 
doi:10.1109/access.2022.3176961 fatcat:6i2pcfrgx5e6fo6ykeykawk4yy

Robust non-local denoising of colored depth data

Benjamin Huhle, Timo Schairer, Philipp Jenke, Wolfgang Strasser
2008 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops  
We give a brief discussion of denoising algorithms for depth data and introduce a novel technique based on the NL-Means Filter.  ...  This robust denoising algorithm takes intra-patch similarity and optional color information into account in order to handle strong discontinuities and to preserve fine detail structure in the data.  ...  The unified denoising technique shows a performance in the outlier detection step comparable to the well-established tensor-voting framework that runs on 3D data.  ... 
doi:10.1109/cvprw.2008.4563158 dblp:conf/cvpr/HuhleSJS08 fatcat:blrzsh7ugrfifd3uqkiczpebgq

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.  ...  To solve the optimization problem, we introduce an efficient iterative algorithm based on variable-splitting and augmented Lagrangian method.  ...  [39] proposed a normal filter based on tensor voting and binary optimization. Furthermore, Yadav et al.  ... 
arXiv:2101.02322v2 fatcat:mi5nzytlcnh23pdnahwo2vfdo4

List of Foreign Periodicals

2019 The Journal of The Institute of Image Information and Television Engineers  
Denoising based on Normal Voting Tensor and Binary Optimization 法線投票と二値最適化に基づくメッシュのノイズ除去 S.K.  ...  Display Combined with Holographic Display and Maxwellian Display using Switchable Holographic Optical Element based on Liquid Lens HOEを用いた透過型ホログラフィックディスプレイ J.S.  ... 
doi:10.3169/itej.73.122 fatcat:k633r5wdwjhnvj2kt2bkby23oe

Surface Denoising based on Normal Filtering in a Robust Statistics Framework [article]

Sunil Kumar Yadav and Martin Skrodzki and Eric Zimmermann and Konrad Polthier
2020 arXiv   pre-print
In this paper, we introduce such a framework to establish relations between a number of widely-used nonlinear filters for face normals in mesh denoising and vertex normals in point set denoising.  ...  The noise-removal process (denoising) can be performed by filtering the surface normals first and by adjusting the vertex positions according to filtered normals afterwards.  ...  Berlin, and the German National Academic  ... 
arXiv:2007.00842v1 fatcat:s3aafj54wfbfpiadkctz6lyfce

A Development Perspective of Point-Based Computer Graphics

Ajahati Mukti
2021 Science Insights  
Based on the digital geometry processing of point-sampled model, various algorithms were reviewed, and some related key techniques were compared with the potential perspective of the future work in this  ...  Every object has its characteristic shape, appearance and responses to physical interactions. Computer graphics center on those three components of an object to bring them onto the computer display.  ...  The similarity-based point model simplification algorithm uses the normal tensor voting method to divide the point model into strong feature edge and non-strong feature edge; the MeanShift clustering method  ... 
doi:10.15354/si.21.re231 fatcat:t4eq72xj4fhtlafmjmzrkutywy

Sparse Regularization-Based Approach for Point Cloud Denoising and Sharp Features Enhancement

Esmeide Leal, German Sanchez-Torres, John W. Branch
2020 Sensors  
In this paper, we present a new model to reconstruct and smooth point clouds that combine L1-median filtering with sparse L1 regularization for both denoising the normal vectors and updating the position  ...  The challenges for a denoising algorithm are noise reduction and sharp features preservation.  ...  The method is robust to the noise and preserves edges and corners. Yadav et al. [25] used Constraint-based normal voting tensor (CVN) analysis and binary optimization to estimate noise-free normal.  ... 
doi:10.3390/s20113206 pmid:32516976 fatcat:efo2pme3vffevk33yyxxx5npqu

Front Matter: Volume 10033

2016 Eighth International Conference on Digital Image Processing (ICDIP 2016)  
.  The last two digits indicate publication order within the volume using a Base 36 numbering system employing both numerals and letters. These two-number sets start with 00, 01, 02, 03, 04,  ...  Utilization of CIDs allows articles to be fully citable as soon as they are published online, and connects the same identifier to all online and print versions of the publication.  ...  based on nonlinear compact multi-scale structure tensor and TV- flow [10033-43] 10033 1B Saliency guided region proposal [10033-154] 10033 1C Retinal automatic segmentation method based on prior  ... 
doi:10.1117/12.2257252 fatcat:v2ipfp2mp5gedjypzpecahpo7e
« Previous Showing results 1 — 15 out of 133 results