GWCNN: A Metric Alignment Layer for Deep Shape Analysis

By Danielle Ezuz, Justin M. Solomon, Vladimir G. Kim, Mirela Ben-Chen. 2017

105 citations recorded by the source corpus.

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

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

Citations in the corpus

Multi-directional geodesic neural networks via equivariant convolution (2018, methodology): “Another recent method [Ezuz et al. 2017] consists in optimizing an embedding of the shape onto the planar domain using intrinsic metric alignment [Solomon et al. 2016].”
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation (2017, methodology): “Another method to learn the surface embedding is to learn a metric alignment layer as in [16], which may require computationally intensive internal optimization during training.”
DiffusionNet: Discretization Agnostic Learning on Surfaces (2020, background): “…multi-view renderings [Kalogerakis et al. 2017; Su et al. 2015; Wei et al. 2016] or more global, often parametrization-based techniques such as panoramas [Sfikas et al. 2017; Shi et al. 2015], geometry images [Sinha et al. 2016], or metric-preserving mappings [Ezuz et al. 2017], among many others.”
3D-CODED: 3D Correspondences by Deep Deformation (2018, background): “…on various shape representations, such as volumetric grids [17,47], point clouds [34,35,16], geometry images [39,38], seamlessly parameterized surfaces [26], by aligning a shape to a grid via distance-preserving maps [15], by folding a surface [48] or by predicting chart representations [18].”
MeshCNN: a network with an edge (2019, methodology): “In its followup work - PointNet++ [Qi et al. 2017], points are partitioned to capture local structures better.”
SPLATNet: Sparse Lattice Networks for Point Cloud Processing (2018, methodology): “Another class of methods embeds the input shapes into 2D parametric domains and then execute convolutions within these domains [38, 26, 13].”
PRNet: Self-Supervised Learning for Partial-to-Partial Registration (2019, methodology): “Other works, including SPLATNet [30], SplineCNN [31], KPConv [32], and GWCNN [33], transform 3D shapes to regular grids for feature learning.”