Sisley the Abstract Painter

Mingtian Zhao         Song-Chun Zhu
University of California, Los Angeles & Lotus Hill Institute


We present an interactive abstract painting system named Sisley. Sisley works upon the psychological principle [Berlyne 1971] that abstract arts are often characterized by their greater perceptual ambiguities than photographs, which tend to invoke moderate mental efforts of the audience for interpretation, accompanied with subtle aesthetic pleasures. Given an input photograph, Sisley decomposes it into a hierarchy/tree of its constituent image components (e.g., regions, objects of different categories) with interactive guidance from the user, then automatically generates corresponding abstract painting images, with increased ambiguities of both the scene and individual objects at desired levels. Sisley consists of three major working parts: (1) an interactive image parser executing the tasks of segmentation, labeling, and hierarchical organization, (2) a painterly rendering engine with abstract operators for transferring the image appearance, and (3) a numerical ambiguity computation and control module of servomechanism. With the help of Sisley, even an amateur user can create abstract paintings from photographs easily in minutes. We have evaluated the rendering results of Sisley using human experiments, and verified that they have similar abstract effects to original abstract paintings by artists.

Paper and Slides

Paper Slides presented at NPAR 2010

Supplemental Copyright Credit Lines to Figure 2
  • Figure 2(a) © The Pollock-Krasner Foundation / Artists Rights Society (ARS), New York
  • Figures 2(b) and 2(c) © Estate of Pablo Picasso / Artists Rights Society (ARS), New York


  author = {Mingtian Zhao and Song-Chun Zhu},
  title = {Sisley the Abstract Painter},
  booktitle = {NPAR '10: Proceedings of the 8th International Symposium on Non-Photorealistic Animation and Rendering},
  year = {2010},
  isbn = {978-1-4503-0125-1},
  pages = {99--107},
  location = {Annecy, France},
  doi = {},
  publisher = {ACM},
  address = {New York, NY, USA},


YouTube WMV YouTube WMV YouTube WMV
1. Interactive Segmentation 2. Hierarchical Organization 3. Object Labeling
YouTube WMV YouTube WMV YouTube WMV
4. Abstract Level Customization 5. Painterly Rendering 6. Result Confirmation


Win32 binary

Updating History
  • January 18, 2012: Updated to Qt 4.8.0
  • July 20, 2011: Various improvements
  • September 30, 2010: Updated to Qt 4.7.0
  • September 1, 2010: DLL dependencies corrected


Related Publications