Shape distributions

By Robert Osada, Thomas A. Funkhouser, Bernard Chazelle, David P. Dobkin. 2002

1,841 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

Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, methodology): “Alternatives include models based on distances, angles, triangle areas, or tetrahedra volumes [23], local shape diameters measured at densely-sampled surface points [3], Heat kernel signatures [1, 17], or extensions of SIFT and SURF feature descriptors to 3D voxel grids [16].”
Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, background): “For example, shapes can be represented with histograms or bag-of-features models constructed out of surface normals and curvatures [15], distances, angles, triangle areas or tetrahedra volumes gathered at sampled surface points [25], properties of spherical functions defined in volumetric grids [16]”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, methodology): “First, we create a shape similarity matrix using the distance between D2 descriptors [22] of shapes in a class.”
Scale-invariant heat kernel signatures for non-rigid shape recognition (2010, methodology): “Rotation and translation invariance can be achieved using volume and area descriptors [45], spherical harmonics [16], geometric moments et al. [38], and distribution of pair-wise Euclidean distances [29].”
Pairwise Decomposition of Image Sequences for Active Multi-view Recognition (2016, background): “Shape descriptors include distributions of local surface properties [14, 32], spherical harmonic functions over voxel grids [24], and 3D local invariant features [25].”
A spectral notion of Gromov–Wasserstein distance and related methods (2011, methodology): “His shape matching proposal is to consider a certain version of the shape distributions idea of [5] in the embedded space.”
3D deep shape descriptor (2015, background): “3D data are often noisy and incomplete after acquisition and meshing [36, 6].”
Depth Information in Human Gait Analysis: An Experimental Study on Gender Recognition (2012, methodology): “Body Shape Feature Extraction:We describe silhouettes in frames using shape distributions, as it is proposed in [8] for general 3D shapes.”
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition (2018, background): “There have been plenty of handcraft 3D descriptors, which can be mainly divided into two categories, i.e., model-based methods [15, 5] and view-based methods [4].”