Edge-aware point set resampling

By Hui Huang, Shihao Wu, Minglun Gong, Daniel Cohen-Or, Uri M. Ascher, Hao Zhang. 2013

478 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. Chi-Wing Fu
4. P. Heng
5. Shihao Wu
6. Yifan Wang
7. Ruihui Li
8. Hui Huang

In Computer Graphics and Computer-Aided Design

1. Daniel Cohen-Or
2. Olga Sorkine-Hornung
3. P. Heng
4. Chi-Wing Fu
5. Shihao Wu
6. Yifan Wang
7. Ruihui Li
8. M. Ovsjanikov

Citations in the corpus

• A review of algorithms for filtering the 3D point cloud (2017, unknown): “Since LOP is an isotropic operator, Huang et al. [55] replaced ) in the term E 1 with following equation where 𝐧 𝑖 denoted normal at point 𝑝 𝑖 , which was estimated based on an anisotropic neighborhood followed by being smoothed using bilateral normal smoothing.”
• State of the Art in Surface Reconstruction from Point Clouds (2014, unknown): “The method of [HWG ∗ 13] allows for the preservation of sharp features in a resampled point cloud by first resampling away from detected edges in order to reliably compute normals and then upsampling in a manner that preserves sharp features, determined by the normals.”
• Differentiable surface splatting for point-based geometry processing (2019, methodology): “Huang et al. [2013] employ an anisotropic weighted locally optimal projection (WLOP) operator [Huang et al. 2009; Lipman et al. 2007] and a progressive edge aware resampling (EAR) procedure to consolidate noisy input.”
• PU-GAN: A Point Cloud Upsampling Adversarial Network (2019, methodology): “[15] further developed a progressive method called EAR for edge-aware resampling of point sets.”
• PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds (2019, methodology): “…jet-fitting, etc.) [FCOS05, CP05, CP07]; consolidating similar patches to cancel out iid noise perturbations (e.g., non-local means, dictionary-based sparse coding), e.g., [Dig12]; or, local smoothing using auxiliary input information (e.g., bilateral smoothing) [HWG ∗ 13], among many others.”
• Patch-Based Progressive 3D Point Set Upsampling (2018, methodology): “Qualitative and quantitative experiments show that our method significantly outperforms the state-of-theart learning-based [58, 59], and optimazation-based [23] approaches, both in terms of handling low-resolution inputs and revealing high-fidelity details.”
• EC-Net: an Edge-aware Point set Consolidation Network (2018, methodology): “In the experiment, we compare our method with state-of-the-art methods, EAR [20], CLOP [21], GPF [51], and PU-Net [7], by applying them to process and consolidate point clouds before the screened Poisson surface reconstruction [48].”
• A Survey of Surface Reconstruction from Point Clouds (2017, unknown): “Similar to the RIMLS approach, the edge-aware resampling (EAR) method [HWG ∗ 13] employs a bilateral mechanism to smooth normals while separating them across sharp features.”
• PU-Net: Point Cloud Upsampling Network (2018, methodology): “Since Edge Aware Resampling (EAR) approach [12] is the state-of-art method for point cloud upsampling, we compare our method with this method.”
• Deep points consolidation (2015, methodology): “Please refer to Berger et al. [2013; 2014] for a more comprehensive survey of state-of-the-art methods.”