Blended intrinsic maps

By Vladimir G. Kim, Yaron Lipman, Thomas A. Funkhouser. 2011

549 citations recorded by the source corpus.

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

In Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, methodology): “Correspondence quality was evaluated using the Princeton benchmark [19], plotting the percentage of matches that are at most r-geodesically distant from the ground-truth correspondence on the reference shape.”
Geometric Deep Learning: Going beyond Euclidean data (2016, background): “[102], [103], [104], [105], [106]) have been devoted to designing local and global features e.”
Learning shape correspondence with anisotropic convolutional neural networks (2016, methodology): “The performance was evaluated using the Princeton protocol [10], plotting the percentage of matches that are at most r-geodesically distant from the groundtruth correspondence on the reference shape.”
Dense Human Body Correspondences Using Convolutional Networks (2015, methodology): “When both source and target shapes are full models, an automatic mapping between shapes with considerable deformations becomes possible as shown in [20, 25, 33, 10].”
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence (2017, methodology): “We measure correspondence quality according to the Princeton benchmark protocol [23].”
Deformable Shape Completion with Graph Convolutional Autoencoders (2017, background): “Dense non-rigid shape correspondence [23, 11, 33, 47, 8] is a fundamental challenge as it is an enabler for many high level tasks like pose or texture transfer across surfaces.”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, methodology): “We use blended intrinsic maps [17] to establish dense correspondence between a mesh model, M and the three exemplar shapes.”
Geometric deep learning (2016, background): “For clothed bodies, the automatic computation of dense mappings [46, 54, 71, 16] has been demonstrated on full surfaces with signiﬁcant shape variations, but are limited to compatible or zero-genus surface topologies.”
PRNet: Self-Supervised Learning for Partial-to-Partial Registration (2019, unknown): “!) possible permutations, most methods (e.g., [34, 35, 36, 37, 38, 39, 40, 41]) compute a sparse set of correspondences and extend them to dense maps, often with bijectivity as an assumption or regularizer.”
Bayesian Inference of Bijective Non-Rigid Shape Correspondence (2016, background): “Of particular interest is the setting in which the objects are allowed to deform non-rigidly.”
Geodesic Convolutional Neural Networks on Riemannian Manifolds (2015, methodology): “Quantitative descriptor evaluation was done using three criteria: cumulative match characteristic (CMC), receiver operator characteristic (ROC), and the Princeton protocol [22].”
Non-Rigid Point Set Registration by Preserving Global and Local Structures (2015, methodology): “For the dataset, we use two pairs of point sets, representing a wolf in different poses from a surface correspondence benchmark3 [40], as shown in the left two columns of Fig.”
Functional maps (2012, methodology): “The majority of existing methods try to tackle these challenges by limiting their search for correspondences between a small set of landmark points and extending those to a dense set of correspondences on entire shapes during final post-processing ([Bronstein et al. 2006; Huang et al. 2008; Lipman a”
Schelling points on 3D surface meshes (2012, methodology): “Maps were constructed with two different meth-ods: 1) manually by interpolating human-selected landmark corre-% spondences (TrueMap), 1 and 2) automatically using Blended Intrinsic Maps [Kim et al. 2011] (BlendedMap).”
Product Manifold Filter: Non-rigid Shape Correspondence via Kernel Density Estimation in the Product Space (2017, methodology): “[25, 20, 21] used conformal embeddings into disks and spheres to parametrize correspondences between homeomorphic surfaces as Möbius transformations.”