Xuexiang Xie
Abstract
The objective of artistic style learning is to synthesize a new image from a source image with the style learnt from example images. Existing example-based texture synthesis (EBTS) techniques model style with low-level statistical properties. These methods work well with some artistic styles such as oil painting, but have difficulties in preserving image details and features for other styles, such as pencil hatching. In this article, an improved artistic style-learning algorithm with feature-based texture synthesis (FBTS) is introduced. Compared with existing EBTS methods, in our FBTS algorithm, image details and features are better defined with a feature field generated from the source image. Also, an improved L2 neighborhood distance metric which provides better measures of perceptual similarity is proposed. Results and comparisons are given to demonstrate the effectiveness of the FBTS algorithm with applications in the areas of stylized shading and artistic style transfer.
- Borgefors, G. 1988. Hierarchical chamfer matching: A parametric edge matching algorithm. IEEE Trans. Pattern Analysis and Machine Intelligence 10, 849--865. Google Scholar
Digital Library
- De Bonet, J. S. 1997. Multiresolution sampling procedure for analysis and synthesis of texture images. In SIGGRAPH Conference Proceedings 1997, 361--368. Google ScholarDigital Library
- Efros, A. and Leung, T. 1999. Texture synthesis by non-parametric sampling. In Proceedings of ICCV, 1033--1038. Google ScholarDigital Library
- Efros, A. and Freeman, W. T. 2001. Image quilting for texture synthesis and transfer. In SIGGRAPH Conference Proceedings 2001, 341--346. Google ScholarDigital Library
- Essa, I., Turk, G., Kwatra, V., Schodl, A., and Bobick, A. 2003. Graphcut textures: Image and video synthesis using graph cuts. In SIGGRAPH Conference Proceedings 2003, 277--286. Google ScholarDigital Library
- Freeman, W. T., Jones, T. R., and Pasztor., E. 2002. Example-based super-resolution. In IEEE Computer Graphics and Applications, 56--65. Google ScholarDigital Library
- Hertzmann, A., Jacobs, C. E., Oliver, N., Curless, B., and Salesin, D. H. 2001. Image analogies. In SIGGRAPH Conference Proceedings 2001, 327--340. Google ScholarDigital Library
- Liang, L., Liu, C., Xu, Y. Q., Guo, B., and Shum, H. Y. 2001. Real-time texture synthesis by patch-based sampling. In ACM Trans. Graphics, 127--150. Google ScholarDigital Library
- Mignotte, M. 2002. Bayesian rendering with non-parametric multiscale prior model. In Proceedings of ICPR02 Conference. Google ScholarDigital Library
- Powell, J. D. 1990. The theory of radial basis function approximation. In Cambridge University Numerical Analysis Report.Google Scholar
- Soler, C., Cani, M. P., and Angelidis, A. 2002. Hierarchical pattern mapping. In SIGGRAPH Conference Proceedings 2002, 673--680. Google ScholarDigital Library
- Tenenbaum, J. B. and Freeman, W. T. 2000. Separating style and content with bilinear models. Neural Computation 12, 6, 1247--1283. Google ScholarDigital Library
- Wei, L. and Levoy, M. 2000. Fast texture synthesis using tree-structured vector quantization. In SIGGRAPH Conference Proceedings 2000, 479--488. Google ScholarDigital Library
- Wu, Q. and Yu, Y. 2004. Feature matching and deformation for texture synthesis. In SIGGRAPH Conference Proceedings 2004. Google ScholarDigital Library
- Xie, X., He, Y., Tian, F., Seah, H. S., Gu, X., and Qin, H. 2007. An effective illustrative visualization framework based on Photic Extremum Lines (PELs). IEEE Trans. Visualization and Computer Graphics 13, 6, 1328--1335. Google ScholarDigital Library
Index Terms
- Style-learning with feature-based texture synthesis
Recommendations
Style learning with feature-based texture synthesis
SPECIAL ISSUE: Media Arts (Part II)The objective of artistic style learning is to synthesize a new image from a source image with the style learnt from example images. Existing example-based texture synthesis (EBTS) techniques model style with low-level statistical properties. These ...
Feature Guided Texture Synthesis (FGTS) for artistic style transfer
DIMEA '07: Proceedings of the 2nd international conference on Digital interactive media in entertainment and artsArtistic images and paintings can be regarded as a composition of content and style. The aim of artistic style transfer is to synthesize a stylized image with content of source image but novel style from style example. Based on texture synthesis, a ...
Synthesis and Rendering of Bidirectional Texture Functions on Arbitrary Surfaces
Abstract--The bidirectional texture function (BTF) is a 6D function that describes the appearance of a real-world surface as a function of lighting and viewing directions. The BTF can model the fine-scale shadows, occlusions, and specularities caused by ...
Comments