Asymptotically Admissible Texture Synthesis
Y.Q. Xu, S.C. Zhu, B.N. guo, and H.Y. Shum
Microsoft Research China and Ohio State Univ.
Recently there is a resurgent interest in example based texture
analysis and synthesis in both computer vision and computer
graphics. While study in computer vision is concerned with
learning accurate texture models, research in graphics is aimed
at effective algorithms for texture synthesis without
necessarily obtaining explicit texture model. This paper makes
three contributions to this recent excitment. First, we
introduce a theoretical framework for designing and analyzing
texture sampling algorithms. This framework, built upon the
mathematical definition of texture, measures a texture sampling
algorithm using admissibility, effectiveness, and sampling
speed. Second, we compare and analyze texture sampling
algorithms based on admissibility and effectiveness. In
particular, we propose different design criteria for texture
analysis algorithm in computer vision and texture synthesis
algorithm in computer graphics. Finally, we develop a novel
texture synthesis algorithm which samples from a subset of the
Julesz ensemble by pasting texture patches from the observed
texture. A ket feature of our algorithm is that it can synthesis
high quality textures extremely fast. On a mid-level PC, we can
synthesize a 512x512 pixel texture image from a 64x64 pixel
example in just 0.03 second. This algorithm has been tested
through extensive experiments and we report sampling results
from our experiments.