Texture Synthesis by Non-Parametric Sampling

Efros, Alexei A.; Leung, Thomas K.

doi:10.1109/ICCV.1999.790383

Texture Synthesis by Non-Parametric Sampling

Alexei A. Efros, Thomas K. Leung

ICCV 1999 pp. 1033-1038

doi:10.1109/ICCV.1999.790383 /iccv/1999/efros1999iccv-texture/

Abstract

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. 1.

PDF ICCV Semantic Scholar

Cite

Text

Efros and Leung. "Texture Synthesis by Non-Parametric Sampling." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.790383

Markdown

[Efros and Leung. "Texture Synthesis by Non-Parametric Sampling." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/efros1999iccv-texture/) doi:10.1109/ICCV.1999.790383

BibTeX

@inproceedings{efros1999iccv-texture,
  title     = {{Texture Synthesis by Non-Parametric Sampling}},
  author    = {Efros, Alexei A. and Leung, Thomas K.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {1033-1038},
  doi       = {10.1109/ICCV.1999.790383},
  url       = {https://mlanthology.org/iccv/1999/efros1999iccv-texture/}
}