Texture synthesis by non-parametric sampling
Alexei A. Efros, T.K. Leung · IEEE International Conference on Computer Vision (ICCV) · 1999
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.
Cited by 3,023 works. doi:10.1109/iccv.1999.790383
Authors
References
- A Mathematical Theory of Communication
- A Mathematical Theory of Communication
- Pyramid-based texture analysis/synthesis
- Modeling and rendering architecture from photographs
- Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
- Multiresolution sampling procedure for analysis and synthesis of texture images
- Texture characterization via joint statistics of wavelet coefficient magnitudes
- Novel cluster-based probability model for texture synthesis, classification, and compression
- Computing Local Surface Orientation and Shape from Texture for Curved Surfaces
- Surface orientation and curvature from differential texture distortion