Non Local Point Set Surfaces

Guillemot, Thierry; Almansa, Andrés; Boubekeur, Tamy

doi:10.1109/3dimpvt.2012.71

Cited by 23 publications

(20 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the supplementary material we include an application that improves an NLM-like algorithm for denoising and interpolation of 3D point clouds [8]. In this case a data structure is definitely required to index and query a set of patches even for point cloud of 10 6 points.…”

Section: Discussionmentioning

confidence: 99%

Covariance Trees for 2D and 3D Processing

Guillemot¹,

Almansa²,

Boubekeur³

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

Gaussian Mixture Models have become one of the major tools in modern statistical image processing, and allowed performance breakthroughs in patch-based image denoising and restoration problems. Nevertheless, their adoption level was kept relatively low because of the computational cost associated to learning such models on large image databases. This work provides a flexible and generic tool for dealing with such models without the computational penalty or parameter tuning difficulties associated to a naïve implementation of GMM-based image restoration tasks. It does so by organising the data manifold in a hirerachical multiscale structure (the Covariance Tree) that can be queried at various scale levels around any point in feature-space. We start by explaining how to construct a Covariance Tree from a subset of the input data, how to enrich its statistics from a larger set in a streaming process, and how to query it efficiently, at any scale. We then demonstrate its usefulness on several applications, including nonlocal image filtering, data-driven denoising, reconstruction from random samples and surface modeling from unorganized 3D points sets.

show abstract

Section: Discussionmentioning

confidence: 99%

Covariance Trees for 2D and 3D Processing

Guillemot¹,

Almansa²,

Boubekeur³

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…In a point set compression framework, [DCV14] proposes a descriptor from which the surface can be locally re‐sampled, based on a local surface height map. Following the success of the non‐local means in image processing [BCM05], similarity‐based denoising has been proposed for surface meshes [YBS06] and point clouds [Dig12, GAB12]. Our method borrows the non‐local processing idea from this thread of work.…”

Section: Related Workmentioning

confidence: 99%

Super‐Resolution of Point Set Surfaces Using Local Similarities

Hamdi-Cherif

Digne

Chaine

2017

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Previous works in image processing [BCM05] attempt to tackle this problem, by introducing the notion of non-local means (NLM). [Dig12] and [GAB12] proposed to exploit the surface self-similarity for surface denoising and meshless geometry processing respectively. Barnes et al [BSFG09] presented an interactive image editing tool by using a randomized algorithm to find similar image patches.…”

Section: Related Workmentioning

confidence: 99%

Data‐Driven Sparse Priors of 3D Shapes

Remil

Xie

et al. 2017

Computer Graphics Forum

View full text Add to dashboard Cite

We present a sparse optimization framework for extracting sparse shape priors from a collection of 3D models. Shape priors are defined as point-set neighborhoods sampled from shape surfaces which convey important information encompassing normals and local shape characterization. A 3D shape model can be considered to be formed with a set of 3D local shape priors, while most of them are likely to have similar geometry. Our key observation is that the local priors extracted from a family of 3D shapes lie in a very low-dimensional manifold. Consequently, a compact and informative subset of priors can be learned to efficiently encode all shapes of the same family. A comprehensive library of local shape priors is first built with the given collection of 3D models of the same family. We then formulate a global, sparse optimization problem which enforces selecting representative priors while minimizing the reconstruction error. To solve the optimization problem, we design an efficient solver based on the Augmented Lagrangian Multipliers method (ALM). Extensive experiments exhibit the power of our data-driven sparse priors in elegantly solving several high-level shape analysis applications and geometry processing tasks, such as shape retrieval, style analysis and symmetry detection.

show abstract

Non Local Point Set Surfaces

Cited by 23 publications

References 29 publications

Covariance Trees for 2D and 3D Processing

Covariance Trees for 2D and 3D Processing

Super‐Resolution of Point Set Surfaces Using Local Similarities

Data‐Driven Sparse Priors of 3D Shapes

Contact Info

Product

Resources

About