Taylor Prediction for Mesh Geometry Compression

In this paper, we introduce a new formalism for mesh geometry prediction. We derive a class of smooth linear predictors from a simple approach based on the Taylor expansion of the mesh geometry function. We use this method as a generic way to compute weights for various linear predictors used for me...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computer graphics forum Jg. 30; H. 1; S. 139 - 151
Hauptverfasser: Courbet, Clément, Hudelot, Céline
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Oxford, UK Blackwell Publishing Ltd 01.03.2011
Wiley
Schlagworte:
Analysis
and object representations - Computational Geometry and Object Modeling
Compressing
Computer graphics
Computer Science
Geometry
geometry compression
Graphics
I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling-Curve
I.3.5 [Computer Graphics]: Computational Geometry and Object Modeling—Curve, surface, solid, and object representations ‐ Computational Geometry and Object Modeling
Image processing systems
mesh compression
parallelogram prediction
solid
Studies
subdivision
surface
Wavelet transforms
ISSN:0167-7055, 1467-8659
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we introduce a new formalism for mesh geometry prediction. We derive a class of smooth linear predictors from a simple approach based on the Taylor expansion of the mesh geometry function. We use this method as a generic way to compute weights for various linear predictors used for mesh compression and compare them with those of existing methods. We show that our scheme is actually equivalent to the Modified Butterfly subdivision scheme used for wavelet mesh compression. We also build new efficient predictors that can be used for connectivity‐driven compression in place of other schemes like Average/Dual Parallelogram Prediction and High Degree Polygon Prediction. The new predictors use the same neighbourhood, but do not make any assumption on mesh anisotropy. In the case of Average Parallelogram Prediction, our new weights improve compression rates from 3% to 18% on our test meshes. For Dual Parallelogram Prediction, our weights are equivalent to those of the previous Freelence approach, that outperforms traditional schemes by 16% on average. Our method effectively shows that these weights are optimal for the class of smooth meshes. Modifying existing schemes to make use of our method is free because only the prediction weights have to be modified in the code.
Bibliographie:ark:/67375/WNG-K0BP1J7J-M
istex:017A36AC31546CC0E85651D2474791CFE233B088
ArticleID:CGF1838
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0167-7055
1467-8659
DOI:10.1111/j.1467-8659.2010.01838.x