Texture synthesis by non-parametric sampling

TLDR

The paper proposes a non‑parametric method for texture synthesis. The method grows a new image pixel by pixel from a seed using a Markov random field model, estimating each pixel’s conditional distribution from similar neighborhoods in the sample image, with randomness tuned by a single perceptually intuitive parameter. The approach preserves local structure and yields high‑quality results across a broad range of synthetic and real‑world textures.

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.