Paint by Relaxation
Author(s): Aaron Hertzmann.
Technical Report: NYU CS, No. 2000-801,
2001.
[BibTeX] 
Abstract:
We use relaxation to produce painted imagery from images and video. An energy function is first specified; a painting is then generated by performing a search for a painting with minimal energy. The appeal of this strategy is that, ideally, we need only specify what we want, not how to directly compute it. Because the energy function is very difficult to optimize, we use a relaxation algorithm combined with various search heuristics.
This formulation allows us to specify painting style by varying the relative weights of energy terms. The basic energy function yields an economical painting that effectively conveys an image with few strokes. This economical style produces moderate temporal coherence when processing video, without losing the essential 2D quality of the painting. The system allows as fine user control as desired: the user may interactively change the painting style, specify variations of style over an image, and/or add specific strokes to the painting. Procedural stroke textures may be used to enhance visual appeal.