We present an algorithm that creates interesting abstract expressionist images from segments of an input image. The algorithm operates by first segmenting the input image at multiple scales, then redistributing the resulting segments across the image plane to obtain an aesthetic abstract output. Larger segments are placed using neighborhood-aware descriptors, and smaller segments are arranged in a Poisson disk distribution. In our thorough analysis, we show that our results score highly according to several relevant aesthetic metrics, and that our style is indeed abstract expressionism. The results are visually appealing, provided the exemplar has a somewhat diverse color pallette and some amount of structure.
A sample of images synthesized by our method. The name given to each image is a pun related to the content of the exemplar.
A virtual 3D art gallery showcasing some of our results.
A high-level overview of our synthesis process. There are two phases: analysis of an input exemplar, then synthesis of a new image.
Images synthesized from exemplars lacking distinct features. Above: exemplar; below: our result.
@article{PALAZZOLO2025104224, title = {Breaking art: Synthesizing abstract expressionism through image rearrangement}, journal = {Computers & Graphics}, volume = {129}, pages = {104224}, year = {2025}, issn = {0097-8493}, doi = {https://doi.org/10.1016/j.cag.2025.104224}, url = {https://www.sciencedirect.com/science/article/pii/S0097849325000652}, author = {Christopher Palazzolo and Oliver {van Kaick} and David Mould}, keywords = {Abstract art synthesis, Image generation, Image segmentation} }
We thank the anonymous reviewers for their valuable feedback. This work was partially supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) and Carleton University. We would also like to thank the members of the Graphics, Imaging, and Games Lab (GIGL) as well as our friends outside the lab for their suggestions and comments.