Title:

Time-Varying Textures

Author(s):

Enrique, Sebastian
Koudelka, Melissa
Belhumeur, Peter N.
Dorsey, Julie
Nayar, Shree K.
Ramamoorthi, Ravi

Date:

2005

Type:

Technical reports

Department:

Computer Science

Permanent URL:

http://hdl.handle.net/10022/AC:P:29388

Series:

Columbia University Computer Science Technical Reports

Part Number:

CUCS-023-05

Publisher:

Department of Computer Science, Columbia University

Publisher Location:

New York

Abstract:

Essentially all computer graphics rendering assumes that the reflectance and texture of surfaces is a static phenomenon. Yet, there is an abundance of materials in nature whose appearance varies dramatically with time, such as cracking paint, growing grass, or ripening banana skins. In this paper, we take a significant step towards addressing this problem, investigating a new class of time-varying textures. We make three contributions. First, we describe the carefully controlled acquisition of datasets of a variety of natural processes including the growth of grass, the accumulation of snow, and the oxidation of copper. Second, we show how to adapt quilting-based methods to time-varying texture synthesis, addressing the important challenges of maintaining temporal coherence, efficient synthesis on large time-varying datasets, and reducing visual artifacts specific to time-varying textures. Finally, we show how simple procedural techniques can be used to control the evolution of the results, such as allowing for a faster growth of grass in well lit (as opposed to shadowed) areas.

Subject(s):

Computer science

Item views:

94

Metadata:

description

View | Download