2016
DOI: 10.1016/j.comgeo.2016.05.005
|View full text |Cite
|
Sign up to set email alerts
|

Analysis of farthest point sampling for approximating geodesics in a graph

Abstract: A standard way to approximate the distance between any two vertices p and q on a mesh is to compute, in the associated graph, a shortest path from p to q that goes through one of k sources, which are well-chosen vertices. Precomputing the distance between each of the k sources to all vertices of the graph yields an efficient computation of approximate distances between any two vertices. One standard method for choosing k sources, which has been used extensively and successfully for isometryinvariant surface pr… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
19
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
1
1

Relationship

0
7

Authors

Journals

citations
Cited by 28 publications
(19 citation statements)
references
References 19 publications
0
19
0
Order By: Relevance
“…In T-Less dataset, the 30 objects are mixed and grouped together to generate 20 sets of images, each set containing 504 images and each image gathering more than one symmetrical object. Since some original CAD object models are not easy to be used in computing surface curvatures, only the traditional technique of farthest point sampling (FPS) [35] is used to sample the 3D keypoints on object surface. We train those T-Less objects one by one and then do the testing with all objects presenting in those 20 sets of images by using the VSD metric.…”
Section: E Results On T-less Datasetmentioning
confidence: 99%
See 1 more Smart Citation
“…In T-Less dataset, the 30 objects are mixed and grouped together to generate 20 sets of images, each set containing 504 images and each image gathering more than one symmetrical object. Since some original CAD object models are not easy to be used in computing surface curvatures, only the traditional technique of farthest point sampling (FPS) [35] is used to sample the 3D keypoints on object surface. We train those T-Less objects one by one and then do the testing with all objects presenting in those 20 sets of images by using the VSD metric.…”
Section: E Results On T-less Datasetmentioning
confidence: 99%
“…The criteria of our keypoint selection are not only to distribute them on the object surface as possible (e.g., like the farthest distance criterion in [35]), but also make them informative and representative for the object shape. In this technique, 3D curvature is an important information used to seek for object keypoints, which leads to a preference of keypoint localization on highly curved surfaces rather than flat, concave, or occluded ones (such as the object body and the flat bottom).…”
Section: A Curvature Point Samplingmentioning
confidence: 99%
“…The FPS method was first introduced for generic graph clustering algorithm [30], and then applied to 2D images [31] and further extended to 3D point cloud [17]. The FPS method has been widely used for a variety of isometry-invariant surface processing tasks [32]. For example, [33] explores this sampling strategy to efficiently esti-mate geodesic distances.…”
Section: Farthest Point Sampling Methodsmentioning
confidence: 99%
“…The computation of shortest geodesic paths (Chen and Han, 1990;Mitchell et al, 1987;Novotni and Klein, 2002) is an important step in many algorithms that address problems in fields of computer science such as motion planning (Hwang and Ahuja, 1992), object representation and recognition (Hamza and Krim, 2003) and dimensionality reduction (Tenenbaum et al, 2000;Onclinx et al, 2010). More specifically, in the area of computer graphics, where triangle meshes are the standard object representation, which can be considered as polyhedra, geodesic paths provide solution to many diverse problems (Peyré et al, 2010;Bose et al, 2011;Ying et al, 2013;Kamousi et al, 2013;Li et al, 2012), including mesh parameterization (Zigelman et al, 2002), mesh watermarking (Wang et al, 2008), shape matching and classification (Hilaga et al, 2001;Bronstein et al, 2010) and shape retrieval (Rabin et al, 2010).…”
Section: Introductionmentioning
confidence: 99%