Texture Synthesis by Non-parametric Sampling
(Picture taken at the CGVV'01 Workshop in Berkeley, CA)
A non-parametric method for texture synthesis is proposed. The texture synthesis process grows a new image outward from an initial seed, one pixel at a time. A Markov random field model is assumed, and the conditional distribution of a pixel given all its neighbors synthesized so far is estimated by querying the sample image and finding all similar neighborhoods. The degree of randomness is controlled by a single perceptually intuitive parameter. The method aims at preserving as much local structure as possible and produces good results for a wide variety of synthetic and real-world textures.
Here is the pseudo code for the algorithm.
Some examples of texture synthesis using our approach are shown below:
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
 |
Examples of constrained texture synthesis (hole-filling) using our approach:
 |
 |
 |
 |
 |
 |
 |
 |