Matching 3D models with shape distributions

By Robert Osada, Thomas A. Funkhouser, Bernard Chazelle, David P. Dobkin. 2001

701 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors (2003, methodology): “(shown in steps (2) and (3) of Figure 1.”
The Princeton Shape Benchmark (2004, methodology): “• Tier image: an image visualizing nearest neighbor, first tier, and second tier matches [23].”
Ensemble of shape functions for 3D object classification (2011, methodology): “The D2 shape function, as introduced by Osada [6], is created by sampling point-pairs from the point cloud and forming a histogram of the distances between these two points.”
Discriminative learning of Markov random fields for segmentation of 3D scan data (2005, methodology): “Some methods (particularly those used for retrieval of 3D models from large databases) use global shape descriptors [6, 17], which require that a complete surface model of the query object is available.”
On Bending Invariant Signatures for Surfaces (2003, background): “In a more recent work, Osada et al. [29] used a variation of this concept by evaluating the probability distribution function (PDF) of a given measure on a 3D surface such as the Euclidean distances between two random points on the surface.”
Recognizing Objects in Range Data Using Regional Point Descriptors (2004, background): “Many approaches to 3D object recognition have been put forth, including generalized cylinders [3], superquadrics [7], geons [23], medial axis representations [1], skeletons [4], shape distributions [19], and spherical harmonic representations of global shape [8].”
Similarity assessment of 3D mechanical components for design reuse (2006, methodology): “Previous studies have proposed a variety of methods for accessing 3D shape similarity [3] [5] [6] [13] [14].”
Paris-Lille-3D: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification (2017, background): “The detailed processing pipeline is: extraction of the ground by region growing on an elevation map, segmentation of objects by connectivity of the remaining point cloud, computation of descriptors on each object (some simple geometric descriptors inspired by [SM14] and some 3D de- scriptor of the l”
Shape matching: similarity measures and algorithms (2001, methodology): “Matching has been approached in a number of ways, including tree pruning [55], the generalized Hough transform [8] or pose clustering [51], geometric hashing [59], the alignment method [27], statistics [40], deformable templates [50], relaxation labeling [44], Fourier descriptors [35], wavelet trans”
Three-dimensional shape searching: state-of-the-art review and future trends (2005, positive): “[126] used shape distributions for the comparison of 3D models.”
A search engine for 3D models (2003, methodology): “[62] represented shapes with probability distributions of geometric properties computed for points randomly sampled on an object’s surface.”
Skeleton based shape matching and retrieval (2003, methodology): “In [24], a 3D shape matching algorithm and system is presented which computes a shape signature for each object and then matches an object into a database of signatures .”