Self-coherent tile set for texture generation

Wanjun Jin; Yifan Shen

doi:10.1117/12.561238

19 March 2004 Self-coherent tile set for texture generation

Wanjun Jin, Yifan Shen

Proceedings Volume 5444, Fourth International Conference on Virtual Reality and Its Applications in Industry; (2004) https://doi.org/10.1117/12.561238
Event: Fourth International Conference On Virtual Reality and Its Applications in Industry, 2003, Tianjin, China

Abstract

In this paper, we present a simple algorithm for texture generation using a set of self-coherent tiles. The tile is called self-coherent if it can be used to tile the plane without discontinuity on the joint. The primary advantage of using a set of tile set for texture generation rather than find-next-at-runtime methods is that once the tiles are found, large expanse of texture can be created very efficiently as needed in real-time. Our tile is created in the process of texture synthesis. Inherence consistency of texture ensures the self-coherence property of synthesized tiles. The method to synthesize self-coherent tile is introduced first. Then, in order to efficiently create as much non-periodic effect as needed, a mechanism is developed to generate a set of such tiles with similar borders but different visual content. Finally the experiment results are shown and the conclusion is made.

Citation Download Citation

Wanjun Jin and Yifan Shen "Self-coherent tile set for texture generation", Proc. SPIE 5444, Fourth International Conference on Virtual Reality and Its Applications in Industry, (19 March 2004); https://doi.org/10.1117/12.561238

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available