Multi-Chart Geometry Images

By Pedro V. Sander, Zoë J. Wood, Steven J. Gortler, John M. Snyder, Hugues Hoppe. 2003

340 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

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].”
An overview of ongoing point cloud compression standardization activities: video-based (V-PCC) and geometry-based (G-PCC) (2020, methodology): “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 a vide”
PolyCube-Maps (2004, unknown): “Other approaches consider larger patches and try to make the parameterization per patch as conformal or areapreserving as possible [Maillot et al. 1993; Lévy et al. 2002; Grimm 2002; Sorkine et al. 2002; Sander et al. 2003].”
Mesh parameterization: theory and practice (2007, background): “planes are developable by definition, one possible approach is to segment the surface into nearly planar charts [Maillot et al., 1993; Garland et al., 2001; Sander et al., 2003; Cohen-Steiner et al., 2004].”
Recent advances in compression of 3D meshes (2005, unknown): “Despite its obvious importance for efficient rendering, this technique reveals a few drawbacks due to the inevitable surface cutting: each geometry image has to be homeomorphic to a disk, therefore closed or genus> 0 models have to be cut along a cut graph to extract either a polygonal schema [7] or”
Recent Advances in Remeshing of Surfaces (2008, methodology): “[70] used an atlas construction to map the input mesh onto charts of arbitrary shape.”
Spectral surface quadrangulation (2006, background): “…images [Gu et al. 2002] produce a fully regular quadrangulation by cutting the mesh into a single component mapped onto a square domain, whereas multichart geometry images [Sander et al. 2003] cut the mesh into regularly sampled patches, improving distortion at the expense of patch continuity.”
Hierarchical mesh segmentation based on fitting primitives (2006, background): “In this context, several approaches are based on region growing ; starting from a few seed points, either randomly selected or determined starting from some geometrical criteria, each region is constructed by expanding the corresponding initial seed [7, 23, 24].”