Recent advances in imaging and multimedia technologies have paved the way for automatic analysis of visual art. Despite notable attempts, extracting relevant patterns from paintings is still a challenging task. Different painters, born in different periods and places, have been influenced by different schools of arts. However, each individual artist also has a unique signature, which is hard to...

In this work we investigate different avenues of improving the Neural Algorithm of Artistic Style [7]. While showing great results when transferring homogeneous and repetitive patterns, the original style representation often fails to capture more complex properties, like having separate styles of foreground and background. This leads to visual artifacts and undesirable textures appearing in un...

By looking at a work of art, an observer enters into a dialogue. In this work, we attempt to analyze this dialogue with both behavioral and computational tools. In two experiments, observers were asked to look at a large number of paintings from different art periods and to rate their visual complexity, or their aesthetic appeal. During these two tasks, their eye movements were recorded. The co...

Screen-style frescoes, found in the temples of Gaoping County, Shanxi Province, China, and originating mostly from the Qing Dynasty, present a unique painting form. Folk artists not only painted the screen, a common object in everyday life in ancient China, on the wall surfaces, but also created a variety of paintings inside the screen panels, whereby the viewer sees a painting within a paintin...

Every night, traditional Irish musicians gather in sessions at pubs and other public spaces to play tunes together. Each public space has its own tradition and history: i.e., context, players, repertoire, styles, etc. Moreover, this tradition is temporally situated; for example, tunes go in and out of fashion. Yet, tunes themselves are mobile—they travel from session to session via recordings, ...

Graphoto is a framework that automatically generates a photo or adjusts an existing one to match a line graph. Since aesthetics is an important element in visualizing personal data, Graphoto provides users with aesthetically pleasing displays for casual line graph information visualization. More specifically, after creating a line graph of the input data, a photo that resembles the input data o...

We present a novel algorithm for stylizing photographs into portrait paintings comprised of curved brush strokes. Rather than drawing upon a prescribed set of heuristics to place strokes, our system learns a flexible model of artistic style by analyzing training data from a human artist. Given a training pair — a source image and painting of that image — a non-parametric model of style is learn...

In recent years, several techniques have been proposed for automatically producing line-art illustrations. In this paper a new non photo-realistic rendering scheme for triangulated surfaces is presented. In contrast to prior approaches with parametric surfaces, there is no global parameterization for triangle meshes. So a new approach is made to automatically generate a direction field for the ...

An artistic rendering method of free-form surfaces with the aid of half-toned text that is laid-out on the given surface is presented. The layout of the text is computed using symbolic composition of the free-form parametric surface S(u, v) with cubic or linear Bézier curve segments C(t) = {cu(t), cv(t)}, comprising the outline of the text symbols. Once the layout is constructed on the surface,...

We present a novel framework for non-photorealistic rendering (NPR) based on view-dependent geometric simplification techniques. Following a common thread in NPR research, we represent the model as a system of particles, which will be rendered as strokes in the final image and which may optionally overlay a polygonal surface. Our primary contribution is the use of a hierarchical view-dependent ...