1,721,195 research outputs found
Learning shape correspondence with anisotropic convolutional neural networks
Full text linkConvolutional neural networks have achieved extraordinary results in many computer vision and pattern recognition applications; however, their adoption in the computer graphics and geometry processing communities is limited due to the non-Euclidean structure of their data. In this paper, we propose Anisotropic Convolutional Neural Network (ACNN), a generalization of classical CNNs to non-Euclidean domains, where classical convolutions are replaced by projections over a set of oriented anisotropic diffusion kernels. We use ACNNs to effectively learn intrinsic dense correspondences between deformable shapes, a fundamental problem in geometry processing, arising in a wide variety of applications. We tested ACNNs performance in challenging settings, achieving state-of-the-art results on recent correspondence benchmarks
Coulomb shapes: using electrostatic forces for deformation-invariant shape representation
No full textCanonical shape analysis is a popular method in deformable shape matching, trying to bring the shape into a canonical form that undoes its non-rigid deformations, thus reducing the problem of non-rigid matching into a rigid one. The canonization can be performed by measuring geodesic distances between all pairs of points on the shape and embedding them into a Euclidean space by means of multidimensional scaling (MDS), which reduces the intrinsic isometries of the shape into the extrinsic (Euclidean) isometries of the embedding space. A notable drawback of MDS-based canonical forms is their sensitivity to topological noise: different shape connectivity can affect dramatically the geodesic distances, resulting in a global distortion of the canonical form. In this paper, we propose a different shape canonization approach based on a physical model of electrostatic repulsion. We minimize the Coulomb energy subject to the local distance constraints between adjacent shape vertices. Our model naturally handles topological noise, allowing to 'tear' the shape at points of strong repulsion. Furthermore, the problem is computationally efficient, as it lends itself to fast multipole methods. We show experimental results in which our method compares favorably to MDS-based canonical forms
Shape-from-intrinsic operator
No full textShape-from-X is an important class of problems in the fields of geometry processing, computer graphics, and vision, attempting to recover the structure of a shape from some observations. In this paper, we formulate the problem of shape-from-operator (SfO), recovering an embedding of a mesh from intrinsic differential operators defined on the mesh. Particularly interesting instances of our SfO problem include synthesis of shape analogies, shape-from-Laplacian reconstruction, and shape exaggeration. Numerically, we approach the SfO problem by splitting it into two optimization sub-problems that are applied in an alternating scheme: metric-from-operator (reconstruction of the discrete metric from the intrinsic operator) and embedding-from-metric (finding a shape embedding that would realize a given metric, a setting of the multidimensional scaling problem)
ShapeNet: Convolutional Neural Networks on Non-Euclidean Manifolds
Full text linkFeature descriptors play a crucial role in a wide range of geometry analysis and processing applications, including shape correspondence, retrieval, and segmentation. In this paper, we propose ShapeNet, a generalization of the popular convolutional neural networks (CNN) paradigm to non-Euclidean manifolds. Our construction is based on a local geodesic system of polar coordinates to extract "patches", which are then passed through a cascade of filters and linear and non-linear operators. The coefficients of the filters and linear combination weights are optimization variables that are learned to minimize a task-specific cost function. We use ShapeNet to learn invariant shape feature descriptors that significantly outperform recent state-of-the-art methods, and show that previous approaches such as heat and wave kernel signatures, optimal spectral descriptors, and intrinsic shape contexts can be obtained as particular configurations of ShapeNet.LTS
Topology Robust Intrinsic Symmetries of non-rigid shapes based on Diffusion Distances
No full text1 online resource (PDF, 37 pages, includes illustrations)Raviv, Dan; Bronstein, Alexander M.; Bronstein, Michael M.; Kimmel, Ron; Sapiro, Guillermo. (2010). Topology Robust Intrinsic Symmetries of non-rigid shapes based on Diffusion Distances. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/180680
Shape-from-Operator: recovering shapes from intrinsic operators
No full textWe formulate the problem of shape-from-operator (SfO), recovering an embedding of a mesh from intrinsic operators defined through the discrete metric (edge lengths). Particularly interesting instances of our SfO problem include: shape-from-Laplacian, allowing to transfer style between shapes; shape-from-difference operator, used to synthesize shape analogies; and shape-from-eigenvectors, allowing to generate 'intrinsic averages' of shape collections. Numerically, we approach the SfO problem by splitting it into two optimization sub-problems: metric-from-operator
(reconstruction of the discrete metric from the intrinsic operator) and embedding-from-metric (finding a shape embedding that would realize a given metric, a setting of the multidimensional scaling problem). We study numerical properties of our problem, exemplify it on several applications, and discuss its imitations
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Coupled functional maps
No full textClassical formulations of the shape matching problem involve the definition of a matching cost that directly depends on the action of the desired map when applied to some input data. Such formulations are typically one-sided - they seek for a mapping from one shape to the other, but not vice versa. In this paper we consider an unbiased formulation of this problem, in which we solve simultaneously for a low-distortion map relating the two given shapes and its inverse. We phrase the problem in the spectral domain using the language of functional maps, resulting in an especially compact and efficient optimization problem. The benefits of our proposed regularization are especially evident in the scarce data setting, where we demonstrate highly competitive results with respect to the state of the art
Shape analysis with anisotropic windowed Fourier transform
No full textWe propose Anisotropic Windowed Fourier Transform (AWFT), a framework for localized space-frequency analysis of deformable 3D shapes. With AWFT, we are able to extract meaningful intrinsic localized orientation-sensitive structures on surfaces, and use them in applications such as shape segmentation, salient point detection, feature point description, and matching. Our method outperforms previous approaches in the considered applications
- …
