Geometry images

By Xianfeng David Gu, Steven J. Gortler, Hugues Hoppe. 2002

937 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

A Papier-Mache Approach to Learning 3D Surface Generation (2018, positive): “The geometry image representation [10, 27] views 3D shapes as functions (e.g., vertex positions) embedded in a 2D domain, providing a natural input for 2D neural networks [28].”
SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (2017, methodology): “Our method to generate 3D shapes surfaces relies on a geometry image representation, i.e . a remesh of an arbitrary surface onto a completely regular grid structure (see [11] and supplement).”
Fundamentals of spherical parameterization for 3D meshes (2003, methodology): “2000; Shapiro and Tal 1998] and remeshing [Gu et al. 2002; Kobbelt 1999] it is best to parameterize the mesh over a domain which is topologically equivalent to it.”
Spherical parametrization and remeshing (2003, methodology): “As shown in Figure 12, our results are better than the compressed geometry images of Gu et al. [2002]. For small file sizes (≤3.”
Single View Reconstruction of Curved Surfaces (2006, methodology): “To optimize this we choose a gridded discretization (recently dubbed the geometry image [5]), representing r by three m × n matrices, X, Y, Z.”
Deep Learning 3D Shape Surfaces Using Geometry Images (2016, methodology): “The traditional approach to create a geometry image is to cut the surface into a disc using a network of cut paths and then map the disc boundary to a square [11].”
An overview of ongoing point cloud compression standardization activities: video-based (V-PCC) and geometry-based (G-PCC) (2020, background): “In contrast to geometry images defined in [26, 27], which store ( x , y , z ) values in three different channels, geometry images in V-PCC store the distance between the missing coordinates of points’ 3D position and the projection surface in the 3D bounding box, using only the luminance channel of…”
Recent advances in compression of 3D meshes (2005, methodology): “[7] proposed a technique for completely regular remeshing of surface meshes using a rectangular grid.”
Feature-based surface parameterization and texture mapping (2005, methodology): “The first of these is to find a single cut of the surface that makes the modified surface topologically equivalent to a disk [Piponi and Borshukov 2000; Gu et al. 2002; Sheffer and Hart 2002; Erickson and Har-Peled 2002; Alliez et al. 2002].”
What Shape Are Dolphins? Building 3D Morphable Models from 2D Images (2013, neutral): “Prasad et al. [10] show how geometry images [18] allow complex topologies to be recovered using a globally convergent quadratic energy minimization.”
Technologies for 3D mesh compression: A survey (2005, methodology): “[108] proposed a scheme called the geometry video coding, which is a generalization of the geometry image coding [76].”