Shape google: Geometric words and expressions for invariant shape retrieval

By A. Bronstein, Michael M. Bronstein, Leonidas J. Guibas, M. Ovsjanikov. 2011

837 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Retrieval & Search

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

In Information Retrieval & Search

Citations in the corpus

Geometric Deep Learning: Going beyond Euclidean data (2016, background): “[102], [103], [104], [105], [106]) have been devoted to designing local and global features e.”
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]”
FPNN: Field Probing Neural Networks for 3D Data (2016, background): “Heat kernel signatures extract shape descriptions by simulating an heat diffusion process on 3D shapes [29, 3].”
FusionNet: 3D Object Classification Using Multiple Data Representations (2016, neutral): “Other shape descriptors include the Light Field Descriptor [3], Heat kernel signatures [2] [12] and SPH [11].”
Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification (2016, methodology): “We follow the standard bag-of-features paradigm [8], where we extract local geometric descriptors, specifically spectral graph wavelet signature (SGWS) [44], and aggregate them with the intrinsic spatial pyramid representation (ISPM) [43].”
MVTN: Multi-View Transformation Network for 3D Shape Recognition (2020, background): “distances, angles, areas, or volumes) to measure the similarity between shapes [1, 9, 7].”
3D all the way: Semantic segmentation of urban scenes from start to end in 3D (2015, methodology): “We follow this vein of research, carrying out facade labeling completely in 3D: from using simple 3D features, point-based classiﬁcation with Random Forests, and with a 3D Conditional Random Field smoothing.”
Efficient Globally Optimal 2D-to-3D Deformable Shape Matching (2016, background): “Numerous works on content-based shape retrieval [8, 32, 5] try to extend popular search paradigms to a setting where the3D query shape is matched to shapes in the database using geometric similarities.”
Learning Spectral Descriptors for Deformable Shape Correspondence (2014, methodology): “…in shape retrieval a global shape descriptor is constructed as a bag of " geometric words " expressed in terms of local feature descriptors [3], [4]; segmentation algorithms rely on the similarity or dissimilarity of feature descriptors to partition the shape into stable and meaningful parts…”