CompAesth 15: Workshop on Computational Aesthetics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/12609

Browse

Now showing 1 - 10 of 10

Frontmatter Expressive 2015
(The Eurographics Association, 2015) Sezgin, Metin; Rosin, Paul L.; Mould, David; Benard, Pierre; Akleman, Ergun; Sezgin, Metin
Painting with Flowsnakes
(The Eurographics Association, 2015) Wyvill, Brian; Paul L. Rosin
Space filling curves, invented by mathematicians in the 19th century, have long been a fascination for artists, however there are no interactive tools to allow an artist to create and explore various levels of recursion of the curve in different parts of the artwork. In this work a new type of painting tool for artists is introduced, which gives the artist control over the very base of a space filling curve, i.e recursive subdivision. Although there are many such curves that would lend themselves to this treatment, the Flowsnake (Gosper) curve has been chosen in this work, mainly for its aesthetics. The curve is based on a hexagonal grid, and in our system hexagons are subdivided at the artist's touch in a non-homogeneous manner, leaving a trail that forms the space filling curve. Some tools are introduced for controlling the painting, such as limiting the depth of recursion, and the 'slow brush', which interpolates slowly between subdivisions to allow the artist to stop at a chosen level. A set of space filling curve brush types provide different shapes and profiles, for giving the artist control of the nonhomogeneous subdivision, including the ability to un-subdivide the hexagons. An algorithm for drawing the curve non-recursively is introduced in order to produce a polyline suitable for processing on the GPU to make the system function at interactive rates. An animated version of the image can be made by replaying the subdivisions from the first level. Some examples made by art students and graduates are shown, along with the artist's comments on the system.
Style-aware Robust Color Transfer
(The Eurographics Association, 2015) Hristova, Hristina; Meur, Olivier Le; Cozot, Rémi; Bouatouch, Kadi; Paul L. Rosin
Transferring features, such as light and colors, between input and reference images is the main objective of color transfer methods. Current state-of-the-art methods focus mainly on the complete transfer of the light and color distributions. However, they do not successfully grasp specific light and color variations in image styles. In this paper, we propose a local method for carrying out a transfer of style between two images. Our method partitions both images to Gaussian distributed clusters by considering their main style features. These features are automatically determined by the classification step of our algorithm. Moreover, we present several novel policies for input/reference cluster mapping, which have not been tackled so far by previous methods. To complete the style transfer, for each pair of corresponding clusters, we apply a parametric color transfer method and a local chromatic adaptation transform. Results, subjective user evaluation as well as objective evaluation show that the proposed method obtains visually pleasing and artifact-free images, respecting the reference style.
Image Warping for a Painterly Effect
(The Eurographics Association, 2015) Li, Jiayu; Mould, David; Paul L. Rosin
We propose a two-stage approach to painterly rendering of photographs, where the image plane is first warped to produce a distorted or caricatured effect and then the resulting image is rendered with a painterly effect. We use SLIC superpixels to obtain an oversegmentation, and assign spring parameters uniformly to all pixels within a region; then, the mass-spring simulation distorts the plane in a random but content-sensitive way. With aggressive warping, the subsequent painterly rendering can be done lightly and need not remove much detail. The resulting renderings convey a sense of being painted and leave a sense of being handmade and not overly beholden to the photographic scene.
Shake it up - Image Decomposition and Rearrangements of Its Constituents
(The Eurographics Association, 2015) Gieseke, Lena; Klingel, Sven; Fuchs, Martin; Paul L. Rosin
Art aspires to surprise an observer and to offer a different perspective. Changing one's perspective enables a deeper understanding of the examined subject and gives insights that are invisible in the original. We propose a method to automatically deconstruct an image into visually coherent constituents and to rearrange those pieces in a surprising, aesthetically pleasing, and potentially informative fashion. Our pipeline is flexible and users can create their individual desired artistic expressions. We show with a survey that the visual appeal of the results vary in regard to the chosen parameter combinations. Lastly, we showcase a variety of examples that explore the design space and hope to show that a reconfiguration in itself presents a new piece of art.
Non-Photorealistic Rendering of Portraits
(The Eurographics Association, 2015) Rosin, Paul L.; Lai, Yu-Kun; Paul L. Rosin
We describe an image-based non-photorealistic rendering pipeline for creating portraits in two styles: The first is a somewhat ''puppet'' like rendering, that treats the face like a relatively uniform smooth surface, with the geometry being emphasised by shading. The second style is inspired by the artist Julian Opie, in which the human face is reduced to its essentials, i.e. homogeneous skin, thick black lines, and facial features such as eyes and the nose represented in a cartoon manner. Our method is able to automatically generate these stylisations without requiring the input images to be tightly cropped, direct frontal view, and moreover perform abstraction while maintaining the distinctiveness of the portraits (i.e. they should remain recognisable).
Image Stylization by Oil Paint Filtering using Color Palettes
(The Eurographics Association, 2015) Semmo, Amir; Limberger, Daniel; Kyprianidis, Jan Eric; Döllner, Jürgen; Paul L. Rosin
This paper presents an approach for transforming images into an oil paint look. To this end, a color quantization scheme is proposed that performs feature-aware recolorization using the dominant colors of the input image. In addition, an approach for real-time computation of paint textures is presented that builds on the smoothed structure adapted to the main feature contours of the quantized image. Our stylization technique leads to homogeneous outputs in the color domain and enables creative control over the visual output, such as color adjustments and per-pixel parametrizations by means of interactive painting.
Rendering Artistic Light Patterns
(The Eurographics Association, 2015) Ji, Li; Gooch, Amy; Gammon, Lynda; Wyvill, Brian; Paul L. Rosin
By combining knowledge from computer graphics and visual arts, we have built a projection installation based on a novel sketch-based shape pattern rendering method. Our novel rendering method is guided by an artist's drawing, and generates shape patterns resembling the input image, creating animation with an organic appearance. We have also applied the proposed method to render foliage shadow effects for virtual scenes. The major contribution of method is its ability to automatically render richly detailed, animated lighting patterns from an approximate lighting plan drawing. In our research team, professional artists and computer graphics researchers work together to develop our rendering method and the artistic rendering projects side by side. This interdisciplinary approach helps us to design and evolve our method for creating aesthetic work with computer graphics technologies.
Computational Models for the Analysis and Synthesis of Graffiti Tag Strokes
(The Eurographics Association, 2015) Berio, Daniel; Leymarie, Frederic Fol; Paul L. Rosin
In this paper we describe a system aimed at the generation and analysis of graffiti tags.We argue that the dynamics of the movement involved in generating tags is in large part - and at a higher degree with respect to many other visual art forms - determinant of their stylistic quality. To capture this notion computationally, we rely on a biophysically plausible model of handwriting gestures (the Sigma Lognormal Model proposed by Réjean Plamondon et al.) that permits the generation of curves which are aesthetically and kinetically similar to the ones made by a human hand when writing. We build upon this model and extend it in order to facilitate the interactive construction and manipulation of digital tags. We then describe a method that reconstructs any planar curve or a sequence of planar points with a set of corresponding model parameters. By doing so, we seek to recover plausible velocity and temporal information for a static trace. We present a number of applications of our system: (i) the interactive design of curves that closely resemble the ones typically observed in graffiti art; (ii) the stylisation and beautification of input point sequences via curves that evoke a smooth and rapidly executed movement; (iii) the generation of multiple instances of a synthetic tag from a single example. This last application is a step in the direction of our longer term plan of realising a system which is capable of automatically generating convincing images in the graffiti style space.
Video Granular Synthesis
(The Eurographics Association, 2015) Forbes, Angus Graeme; Villegas, Javier; Paul L. Rosin
This paper introduces a technique that enables the creative reshaping of one or more video signals based on granular synthesis techniques, normally applied only to audio signals. We demonstrate that a wide range of novel video processing effects can be generated through conceptualizing a video signal as being composed of a large number of video grains. These grains can be manipulated and maneuvered in a variety of ways, and a new video signal can then be created through the resynthesis of these altered grains; effects include cloning, rotating, and resizing the video grains, as well as repositioning them in space and time. These effects have been used successfully in a series of interactive multimedia performances, leading us to believe that our approach has significant artistic potential.

Browse

Browsing CompAesth 15: Workshop on Computational Aesthetics by Issue Date

Results Per Page

Sort Options