Non‐Local Low‐Rank Normal Filtering for Mesh Denoising

Li, Xianzhi; Zhu, Lei; Fu, Chi‐Wing; Heng, Pheng‐Ann

doi:10.1111/cgf.13556

Cited by 39 publications

(56 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 9 (Nicolo:σ n = 0.2l e and Vaselion:σ n = 0.2l e ) shows two such examples. We can observe from Figure 9 (Nicolo:σ n = 0.2l e ) that our method and NLLR [58] generates similar results which are the best among all results. NLLR [58] uses non-local information for mesh smoothing while our method uses local information only.…”

Section: Visual Resultsmentioning

confidence: 65%

“…Our method produces very competitive results, in terms of preserving features. Taking the second row as example, our HLO and NLLR [58] produce the best results while other methods may oversharpen or oversmooth certain regions. Note that NLLR [58] uses non-local information while ours utilizes local information only.…”

Section: Visual Resultsmentioning

confidence: 99%

“…In this work, we have introduced a novel method for featurepreserving surface smoothing. Motivated by the shrinking and (c) BMF [36] (d) UNF [45] (e) BNF [37] (f) L0 [7] (g) GNF [43] (h) CNR [49] (i) NLLR [58] (j) Ours feature-wiping issues of the uniform Laplacian operator, we analyzed the differential property at feature points. We developed a Half-kernel Laplacian Operator (HLO) which can preserve surface features and resist shrinkage.…”

Section: Resultsmentioning

confidence: 99%

“…Noisy UNF [45] BNF [37] L0 [7] GNF [43] CNR [49] NLLR [58] Ours Figure 9: Models corrupted with Gaussian noise: Bunny σ n = 0.5l e , Nicolo σ n = 0.2l e and σ n = 0.5l e , Vaselion σ n = 0.2l e and σ n = 0.8l e . The flipped triangles are rendered in red.…”

Section: Resultsmentioning

confidence: 99%

“…The compared state-of-the-art techniques are: the bilateral mesh filter (BMF) [36], the unilateral normal filter (UNF) [45], the bilateral normal filter (BNF) [37], the L 0 minimization method (L 0 ) [7], the guided normal filter (GNF) [43], the cascaded normal regression (CNR) [49], and the non-local low-rank normal filtering method (NLLR) [58]. The source code of these methods are available or the authors provide test results.…”

Section: Parameter Settingmentioning

confidence: 99%

See 4 more Smart Citations

HLO: Half-kernel Laplacian operator for surface smoothing

Pan

Gong

et al. 2020

Computer-Aided Design

View full text Add to dashboard Cite

This paper presents a simple yet effective method for feature-preserving surface smoothing. Through analyzing the differential property of surfaces, we show that the conventional discrete Laplacian operator with uniform weights is not applicable to feature points at which the surface is non-differentiable and the second order derivatives do not exist. To overcome this difficulty, we propose a Half-kernel Laplacian Operator (HLO) as an alternative to the conventional Laplacian. Given a vertex v, HLO first finds all pairs of its neighboring vertices and divides each pair into two subsets (called half windows); then computes the uniform Laplacians of all such subsets and subsequently projects the computed Laplacians to the full-window uniform Laplacian to alleviate flipping and degeneration. The half window with least regularization energy is then chosen for v. We develop an iterative approach to apply HLO for surface denoising. Our method is conceptually simple and easy to use because it has a single parameter, i.e., the number of iterations for updating vertices. We show that our method can preserve features better than the popular uniform Laplacian-based denoising and it significantly alleviates the shrinkage artifact. Extensive experimental results demonstrate that HLO is better than or comparable to state-of-the-art techniques both qualitatively and quantitatively and that it is particularly good at handling meshes with high noise. We will make our source code publicly available.

show abstract

Section: Visual Resultsmentioning

confidence: 65%

Section: Visual Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Parameter Settingmentioning

confidence: 99%

See 3 more Smart Citations

HLO: Half-kernel Laplacian operator for surface smoothing

Pan

Gong

et al. 2020

Computer-Aided Design

View full text Add to dashboard Cite

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