Multi‐scale Feature Extraction on Point‐Sampled Surfaces

By Mark Pauly, Richard Keiser, Markus H. Gross. Computer graphics forum (Print), 2003

616 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/9e7016e0b6dbaa74ff7e275ac2612c3fc9a26525

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

In Computer Graphics and Computer-Aided Design

In Geology

Citations in the corpus

Ridge-valley lines on meshes via implicit surface fitting (2004, methodology): “In geometric modeling, there has been considerable effort to develop robust methods for crease detection on dense triangle meshes [Watanabe and Belyaev 2001; Hubeli and Gross 2001; Page et al. 2002; Stylianou and Farin 2003] and point-sampled surfaces [Gumhold et al. 2001; Pauly et al. 2003].”
FAST SEMANTIC SEGMENTATION OF 3D POINT CLOUDS WITH STRONGLY VARYING DENSITY (2016, background): “We found that features derived from the structure tensor and the vertical point distribution work well over a wide range of scales, and are particularly fast when combined with an efﬁcient approximation of a point’s multi-scale neighborhood (Pauly et al., 2003).”
Intrinsic shape context descriptors for deformable shapes (2012, background): “Classical works in this category include the integral volume descriptors [29, 17], spin images [21] and multiscale local features [32] just to mention a few out of many.”
Reassembling fractured objects by geometric matching (2006, methodology): “For multi-scale edge extraction we use a modified version of the method presented by [Pauly et al. 2003].”
3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey (2014, methodology): “[92] measured the surface variation d by using the eigenvalues 1, 2 and 3 of the covariance matrix of the neighboring points, that is d 1⁄4 3 ð 1 þ 2 þ 3Þ.”
Persistent Point Feature Histograms for 3D Point Clouds (2008, background): “scale) for normal estimation on 3D point cloud data [8,9] as well as principal curvatures [ 10 ,11,12] on multiple scales.”
Aligning point cloud views using persistent feature histograms (2008, methodology): “scale) for normal estimation on 3D point cloud data [10], [11] as well as principal curvatures [12], [13], [14] on multiple scales.”
Scale selection for classification of point-sampled 3D surfaces (2005, background): “Work in [6] classifies points based on eigenvalues of the local covariance matrix in its n-neighborhood.”
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera (2013, background): “Although depth data has existed for several decades, the interest point detection and description has stayed at the level of describing static scenes or objects for a long time [24, 16, 23].”
Voronoi-Based Curvature and Feature Estimation from Point Clouds (2011, background): “The location of sharp edges and highly curved areas of the surface is a precious piece of information in settings that include feature-aware reconstruction [JWS08], non photorealistic rendering [PKG03], and industrial metrology.”
Learning class‐specific descriptors for deformable shapes using localized spectral convolutional networks (2015, background): “Descriptors like spin images [JH99], shape distributions [OFCD02], integral volume descriptors [MCH ∗ 06], and multi-scale features [PKG03] are based on extrinsic structure of the shape and therefore invariant under Euclidean transformations, but not under deformations.”
Scale-invariant heat kernel signatures for non-rigid shape recognition (2010, methodology): “Different approaches such as contour and edge features [30] [18], spin images [14], local patches [28] [42], conformal factor [4], differential operators [44], and local volume properties [13] were used as feature descriptors in the shape retrieval literature.”