Salience-adaptive Painterly Rendering Using Genetic Search

We present a new non-photorealistic rendering (NPR) algorithm for rendering photographs in an impasto painterly style. We observe that most existing image-based NPR algorithms operate in a spatially local manner, typically as non-linear image filters seeking to preserve edges and other high-frequency content. By contrast, we argue that figurative artworks are salience maps, and develop a novel painting algorithm that uses a genetic algorithm (GA) to search the space of possible paintings for a given image, so approaching an "optimal" artwork in which salient detail is conserved and non-salient detail is attenuated. Differential rendering styles are also possible by varying stroke style according to the classification of salient artifacts encountered, for example edges or ridges. We demonstrate the results of our technique on a wide range of images, illustrating both the improved control over level of detail due to our salience adaptive painting approach, and the benefits gained by subsequent relaxation of the painting using the GA.

[1]  Michio Shiraishi,et al.  An algorithm for automatic painterly rendering based on local source image approximation , 2000, NPAR '00.

[2]  Aaron Hertzmann,et al.  Fast paint texture , 2002, NPAR '02.

[3]  Yunhe Pan,et al.  Advanced Design for a Realistic Virtual Brush , 2003, Comput. Graph. Forum.

[4]  Alan Woods,et al.  Gombrich's Art and Illusion , 1981 .

[5]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[6]  Peter Litwinowicz,et al.  Processing images and video for an impressionist effect , 1997, SIGGRAPH.

[7]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[8]  Aaron Hertzmann,et al.  Painterly rendering with curved brush strokes of multiple sizes , 1998, SIGGRAPH.

[9]  Peter M. Hall,et al.  Learning to detect low-level features , 2004, BMVC.

[10]  John Collomosse,et al.  Painterly rendering using image salience , 2002, Proceedings 20th Eurographics UK Conference.

[11]  Peter Shirley,et al.  Artistic Vision: painterly rendering using computer vision techniques , 2002, NPAR '02.

[12]  W D Wright,et al.  Color Science, Concepts and Methods. Quantitative Data and Formulas , 1967 .

[13]  Francisco Herrera,et al.  Learning with Genetic Algorithms , 2001 .

[14]  Paul Haeberli,et al.  Paint by numbers: abstract image representations , 1990, SIGGRAPH.

[15]  Tamás Szirányi,et al.  Random paintbrush transformation , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[16]  John Philip Collomosse,et al.  Higher level techniques for the artistic rendering of images and video , 2004 .

[17]  J. Andrew Bangham,et al.  The Art of Scale-Space , 2003, BMVC.

[18]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[19]  Taein Lee,et al.  Active contour models , 2005 .

[20]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[21]  Timothy F. Cootes,et al.  Locating Salient Object Features , 1998, BMVC.

[22]  Kenneth DeJong,et al.  Learning with genetic algorithms: An overview , 1988, Machine Learning.

[23]  Douglas DeCarlo,et al.  Abstracted painterly renderings using eye-tracking data , 2002, NPAR '02.

[24]  Erol Gelenbe,et al.  Learning in Genetic Algorithms , 1998, ICES.

[25]  Aaron Hertzmann,et al.  Paint by relaxation , 2001, Proceedings. Computer Graphics International 2001.

[26]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[27]  John P. Collomosse,et al.  A trainable low-level feature detector , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[28]  Nahum D. Gershon.  Visualization Blackboard-visualizing 3D PET images , 1991, IEEE Computer Graphics and Applications.