Figure 1: Abstraction examples. Original: Snapshots of a guard in Petra (left) and two business students (right). Abstracted: After several bilateral filtering passes and with DoG-edges overlayed. Quantized: Luminance channel soft-quantized to 12 bins (left) and 8 bins (right). Note how folds in the clothing and other image details are emphasized (stones on left and student's shadows on right). AbstractWe present an automatic, real-time video and image abstraction framework that abstracts imagery by modifying the contrast of visually important features, namely luminance and color opponency. We reduce contrast in low-contrast regions using an approximation to anisotropic diffusion, and artificially increase contrast in higher contrast regions with difference-of-Gaussian edges. The abstraction step is extensible and allows for artistic or data-driven control. Abstracted images can optionally be stylized using soft color quantization to create cartoon-like effects with good temporal coherence. Our framework design is highly parallel, allowing for a GPU-based, real-time implementation. We evaluate the effectiveness of our abstraction framework with a user-study and find that participants are faster at naming abstracted faces of known persons compared to photographs. Participants are also better at remembering abstracted images of arbitrary scenes in a memory task.

Recent extensions to the standard difference-of-Gaussians (DoG) edge detection operator have rendered it less susceptible to noise and increased its aesthetic appeal. Despite these advances, the technical subtleties and stylistic potential of the DoG operator are often overlooked. This paper offers a detailed review of the DoG operator and its extensions, highlighting useful relationships to other image processing techniques. It also presents many new results spanning a variety of styles, including pencil-shading, pastel, hatching, and woodcut. Additionally, we demonstrate a range of subtle artistic effects, such as ghosting, speed-lines, negative edges, indication, and abstraction, all of which are obtained using an extended DoG formulation, or slight modifications thereof. In all cases, the visual quality achieved by the extended DoG operator is comparable to or better than those of systems dedicated to a single style.

Figure 1: Abstraction examples. Original: Snapshots of a guard in Petra (left) and two business students (right). Abstracted: After several bilateral filtering passes and with DoG-edges overlayed. Quantized: Luminance channel soft-quantized to 12 bins (left) and 8 bins (right). Note how folds in the clothing and other image details are emphasized (stones on left and student's shadows on right). AbstractWe present an automatic, real-time video and image abstraction framework that abstracts imagery by modifying the contrast of visually important features, namely luminance and color opponency. We reduce contrast in low-contrast regions using an approximation to anisotropic diffusion, and artificially increase contrast in higher contrast regions with difference-of-Gaussian edges. The abstraction step is extensible and allows for artistic or data-driven control. Abstracted images can optionally be stylized using soft color quantization to create cartoon-like effects with good temporal coherence. Our framework design is highly parallel, allowing for a GPU-based, real-time implementation. We evaluate the effectiveness of our abstraction framework with a user-study and find that participants are faster at naming abstracted faces of known persons compared to photographs. Participants are also better at remembering abstracted images of arbitrary scenes in a memory task.

Figure 1: A color image (Left) often reveals important visual details missing from a luminance-only image (Middle). Our Color2Gray algorithm (Right) maps visible color changes to grayscale changes. Image: Impressionist Sunrise by Claude Monet, courtesy of Artcyclopedia.com. AbstractVisually important image features often disappear when color images are converted to grayscale. The algorithm introduced here reduces such losses by attempting to preserve the salient features of the color image. The Color2Gray algorithm is a 3-step process: 1) convert RGB inputs to a perceptually uniform CIE L * a * b * color space, 2) use chrominance and luminance differences to create grayscale target differences between nearby image pixels, and 3) solve an optimization problem designed to selectively modulate the grayscale representation as a function of the chroma variation of the source image. The Color2Gray results offer viewers salient information missing from previous grayscale image creation methods.

We present an interactive system which allows users to create abstract paintings in the style of Jackson Pollock using three dimensional viscous fluid jets. Pollock's paintings were created by using streams of household paint to make guided, semi-random patterns on his canvas. Our fluid jet model consists of two coupled simulations: a Navier-Stokes solver for an axis-symmetric fluid column and a linked-mass system for tracking the three dimensional motion of the jet's axis line. The paint trails left by the jets are represented using implicit surfaces. Our system also includes an algorithm for generating the splatter patterns created by the impacts of a highspeed fluid drops. We allow users to analyze the fractal properties of the images they create, comparing them to those known to exist in Pollock's own paintings. Introduction and VisionIn the late 1940s, the American painter Jackson Pollock developed a style of painting later deemed Abstract Expressionism. He rolled a large canvas across the floor of his barn onto which he dripped, drizzled and poured household paint. His technique generated a sensation among critics accustomed to traditional brush strokes.With this seemingly simple painting technique, Pollock managed to create paintings with widely differing visual styles. Common to all of these paintings, however, is Pollock's unique usage of fluid trails of varying widths. The formulation of these trails depends on the interplay between the artist's stroke motion and the dynamics of thin, viscous fluids. In order to simulate this interaction, it is critical to have an interface and real-time fluid model that considers all influencing factors; velocity, gravity, viscosity and surface tension. However, since current 3D fluid jet simulation techniques proved too computationally costly to be used in our real-time application, we developed a stable fluid jet model which couples two different fluid types with reduced dimensions. This allows interactive simulation while still preserving the characteristic fluid behaviors of Pollock's paintings.Recent mathematical analysis indicates that the fluid jet patterns of Pollock's painting may be related to fractal structure. Pollock's paintings contain self-similar patterns which contribute to the aesthetic quality of the work. This may suggest a correlation between the statistical properties of some abstract art and its aesthetic value. While computers can calculate these properties explicitly, humans * may only be able to recognize them subconsciously. As Pollock's painting style matured, the fractal dimension of his images increased. Our system includes an evaluation tool which calculates the fractal dimensions of a user's painting. Users can both create Abstract Expressionist images while analyzing the work's fractal properties. Unlike real-world paintings, our digital system makes users aware of fractal properties interactively, and they can compare the fractal characteristics of each individual's work easily. Our vision is of tools that both engage and inform the ar...