GPU-based approaches for shape diameter function computation and its applications focused on skeleton extraction

Baldacci, A.; Kamenický, Rastislav; Riečický, Adam; Cignoni, Paolo; Ďurikovič, Roman; Scopigno, Roberto; Madaras, Martin

doi:10.1016/j.cag.2016.06.006

Cited by 9 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditional shape descriptor‐based segmentation methods [BKR*16, BK10] can be easily extended to high‐resolution mesh segmentation, but these methods cannot achieve good results due to the lack of semantic meanings for 3D shapes. Although deep learning‐based methods [XLZ*20] can access semantic meanings, it is difficult for these methods to implement high‐resolution mesh segmentation due to limited computing resources.…”

Section: Related Workmentioning

confidence: 99%

MeshFormer: High‐resolution Mesh Segmentation with Graph Transformer

Jiang

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Graph transformer has achieved remarkable success in graph‐based segmentation tasks. Inspired by this success, we propose a novel method named MeshFormer for applying the graph transformer to the semantic segmentation of high‐resolution meshes. The main challenges are the large data size, the massive model size, and the insufficient extraction of high‐resolution semantic meanings. The large data or model size necessitates unacceptably extensive computational resources, and the insufficient semantic meanings lead to inaccurate segmentation results. MeshFormer addresses these three challenges with three components. First, a boundary‐preserving simplification is introduced to reduce the data size while maintaining the critical high‐resolution information in segmentation boundaries. Second, a Ricci flow‐based clustering algorithm is presented for constructing hierarchical structures of meshes, replacing many convolutions layers for global support with only a few convolutions in hierarchy structures. In this way, the model size can be reduced to an acceptable range. Third, we design a graph transformer with cross‐resolution convolutions, which extracts richer high‐resolution semantic meanings and improves segmentation results over previous methods. Experiments show that MeshFormer achieves gains from 1.0% to 5.8% on artificial and real‐world datasets.

show abstract

Section: Related Workmentioning

confidence: 99%

MeshFormer: High‐resolution Mesh Segmentation with Graph Transformer

Jiang

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Swept volumes and collision detection. Our methodology for quickly determining nesting feasibility is heavily influenced by “depth peeling”‐type methods that have been used for GPU‐acceleration of constructive solid geometry visualization [GHF86, KGP*94, HR05], order‐independent transparency [Eve01, BCL*07], CNC milling simulation [IO07], and shape diameter estimation [BKR*16]. Similarly, layered depth images [SGHS98] (originally presented for image based rendering) have been leveraged for intersection volume computation [FBAF08], collision detection [MOK95, HTG03, KP03] and swept volumes for minimal interference‐removing translations [KOLM02].…”

Section: Related Workmentioning

confidence: 99%

Generalized Matryoshka: Computational Design of Nesting Objects

Jacobson

2017

Computer Graphics Forum

View full text Add to dashboard Cite

This paper generalizes the self‐similar nesting of Matryoshka dolls (“Russian nesting dolls”) to arbitrary solid objects. We introduce the problem of finding the largest scale replica of an object that nests inside itself. Not only should the nesting object fit inside the larger copy without interpenetration, but also it should be possible to cut the larger copy in two and remove the smaller object without collisions. We present a GPU‐accelerated evaluation of nesting feasibility. This test can be conducted at interactive rates, providing feedback during manual design. Further, we may optimize for some or all of the nesting degrees of freedom (e.g., rigid motion of smaller object, cut orientation) to maximize the smaller object's scale while maintaining a feasible nesting. Our formulation and tools robustly handle imperfect geometric representations and generalize to the nesting of dissimilar objects in one another. We explore a variety of applications to aesthetic and functional shape design.

show abstract

“…S EVERAL works have shown the benefits of Fibonaccibased spherical distributions of points for various applications [2], [4], [10], [17], [19], [29]. The main strength of these point sets is an extremely uniform distribution which is near-optimal in terms of spherical cap discrepancy [5].…”

Section: Introductionmentioning

confidence: 99%

“…In the particular case of computer graphics, SFGs have been successfully used for Quasi-Monte Carlo (QMC) spherical integration [19], vector quantization, texture filtering and procedural modeling [17], and, more recently, cone sampling for computation of the Shape Diameter Function [4]. In all these applications, the SFGs are shown to be more effective than alternative methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extensible Spherical Fibonacci Grids

Marques

Bouville

Bouatouch

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Spherical Fibonacci grids (SFG) yield extremely uniform point set distributions on the sphere. This feature makes SFGs particularly well-suited to a wide range of computer graphics applications, from numerical integration, to vector quantization, among others. However, the application of SFGs to problems in which further refinement of an initial point set is required is currently not possible. This is because there is currently no solution to the problem of adding new points to an existing SFG while maintaining the point set properties. In this work, we fill this gap by proposing the extensible spherical Fibonacci grids (E-SFG). We start by carrying out a formal analysis of SFGs to identify the properties which make these point sets exhibit a nearly-optimal uniform spherical distribution. Then, we propose an algorithm (E-SFG) to extend the original point set while preserving these properties. Finally, we compare the E-SFG with a other extensible spherical point sets. Our results show that the E-SFG outperforms spherical point sets based on a low discrepancy sequence both in terms of spherical cap discrepancy and in terms of root mean squared error for evaluating the rendering integral.

show abstract

GPU-based approaches for shape diameter function computation and its applications focused on skeleton extraction

Cited by 9 publications

References 13 publications

MeshFormer: High‐resolution Mesh Segmentation with Graph Transformer

MeshFormer: High‐resolution Mesh Segmentation with Graph Transformer

Generalized Matryoshka: Computational Design of Nesting Objects

Extensible Spherical Fibonacci Grids

Contact Info

Product

Resources

About