Computational Aesthetics: EG Workshop on Computational Aesthetics in Graphics, Visualization and Imaging

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/314

Browse

Now showing 1 - 20 of 185

Abstraction and Depiction of Sparsely Scanned Outdoor Environments
(The Eurographics Association, 2005) Xu, Hui; Gossett, Nathan; Chen, Baoquan; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
This paper describes various techniques and applications of rendering three-dimensionally digitized outdoor en- vironments in non-photorealistic rendering styles. The difficulty in rendering outdoor environments is accommodating their inaccuracy, incompleteness, and large size to deliver a smooth animation without suggesting the underlying data deficiency. Standard rendering approaches often expose and inadvertently emphasize missing and noisy data, producing unpleasant images. Our use of non-photorealistic rendering allows us to de-emphasize these problems and produce aesthetically pleasing images. The key approach discussed in this paper employs artistic drawing techniques to illustrate features of varying importance and accuracy. We use point-based representations of the scanned environments and operate directly on the point-based models for abstraction and rendering. We de- velop a unified framework for producing sketchy, profile, painterly, cartoon, and intermingled styles. We describe a level-of-detail data structure, the continuous resolution queue, to promise coherent and consistent animation. We also leverage modern graphics hardware to achieve interactive rendering of large scenes.
Accurate and Discernible Photocollages
(The Eurographics Association, 2012) Miller, Jordan; Mould, David; Douglas Cunningham and Donald House
We propose a system for arranging images from a database into a collage that resembles some target image. These collages exploit large scale visual correspondences between the target image and the images in the database. We ensure that images of multiple sizes are used and are combined so that boundaries between images are not immediately apparently; as a result, the final collage consists of irregularly shaped image sections. The final collages contain a dynamic mixture of textures, images, and shapes that is in contrast to the geometric and regular character of many photomosaic techniques. In service of these tasks, we propose a fast scale-based method for querying an image library, a novel method for composing multiple images using geodesic distance Voronoi tesselations, and a novel base/detail method for shifting the colors of the final collage so that the target image is more accurately represented.
ActionPlot: A Visualization Tool for Contemporary Dance Analysis
(The Eurographics Association, 2011) Carlson, K.; Schiphorst, T.; Shaw, C.; Douglas Cunningham and Tobias Isenberg
This paper illustrates a prototype for visualizing contemporary dance through a movement analysis tool, entitled ActionPlot. Contemporary dance is an experiential and time based art form with few available analysis techniques. Our design facilitates structural analysis of dance performance by codifying and plotting expert viewer information. ActionPlot is then useful to experts familiar with choreographic strategies and illustrates three levels; viewing for interpretation or meaning, for structural or performative information or for detailed movement information. Plotted elements include the number of performers, the performer's attention and intention, the amount of effort used,tempo of the effort, the balance of the movement within the body and the time the action is performed. This process conveys information about the viewing experience in context, allowing the user to see structural and performative patterns, similarities and differences while comparing between two works. We detail our motivation, design decisions, implementation and a qualitative evaluation for the presented system.
Adding Lighting and Viewing Effects to Digital Images
(The Eurographics Association, 2009) Grimm, Cindy; Oliver Deussen and Peter Hall
Real paintings are not truly flat but change subtly with variations in viewing direction. The pigments and painting layers also interact with the lighting environment, producing changes that range from subtle to quite dramatic. These effects are lacking in digital images. This paper describes a system that allows an artist to introduce, and control, a variety of lighting and viewing effects, such as specular reflection and refraction, through the use of additional images.
Aesthetic Agents: Swarm-based Non-photorealistic Rendering using Multiple Images
(The Eurographics Association, 2011) Love, J.; Pasquier, P.; Wyvill, B.; S.Gibson,; Tzanetakis, G.; Douglas Cunningham and Tobias Isenberg
The creation of expressive styles for digital art is one of the primary goals in non-photorealistic rendering. In this paper, we introduce a swarm-based multi-agent system that is capable of producing expressive imagery through the use of multiple digital images. At birth, agents in our system are assigned a digital image that represents their 'aesthetic ideal'. As agents move throughout a digital canvas they try to 'realize' their ideal by modifying the pixels in the digital canvas to be closer to the pixels in their aesthetic ideal. When groups of agents with different aesthetic ideals occupy the same canvas, a new image is created through the convergence of their conflicting aesthetic goals. We use our system to explore the concepts and techniques from a number of Modern Art movements. The simple implementation and effective results produced by our system makes a compelling argument for more research using swarm-based multi-agent systems for non-photorealistic rending.
Aesthetic Appraisal of Art - from Eye Movements to Computers
(The Eurographics Association, 2009) Wallraven, Christian; Cunningham, Douglas W.; Rigau, Jaume; Feixas, Miquel; Sbert, Mateu; Oliver Deussen and Peter Hall
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 complexity and aesthetic ratings show clear preferences for certain artistic styles and were based on both low-level and high-level criteria. Eye movements reveal the time course of the aesthetic dialogue as observers try to interpret and understand the painting. Computational analyses of both the ratings (using measures derived from information theory) and the eye tracking data (using two models of saliency) showed that our computational tools are already able to explain some properties of this dialogue.
Aesthetic Placement of Points Using Generalized Lloyd Relaxation
(The Eurographics Association, 2009) Deussen, Oliver; Oliver Deussen and Peter Hall
In this paper we describe a computational method for producing aesthetically pleasing distributions of disks on a canvas. The positions of the disks are initially given at random and are moved into interesting configurations by means of a local optimization routine. The configurations are computed by a Voronoi-cell based optimization algorithm (Lloyd's relaxation method). We extend this method in a way that not only evenly spaced but also clustered point sets can be produced. This is done by inverting the iterative step of the optimization algorithm. We define an energy term and show that for a certain amount of energy interesting configurations appear. This is evaluated in a small user study.
Aesthetics in Covariant Image Reconstruction
(The Eurographics Association, 2005) Georgiev, Todor; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
This paper describes a method of seamless cloning based on aesthetic theory of lightness perception. Judgment of lightness and color harmony is treated as low level aesthetic judgment made by the human visual system. The equation written based on this consideration is an improvement to Poisson image editing, and produces results that are better than the current state of the art in the area of scratch/object removal. The reason our result is aesthetically pleasing is that it is fundamentally based on aesthetic theory, and it proves the usefulness of our theoretical approach.
The Aesthetics of Graph Visualization
(The Eurographics Association, 2007) Bennett, Chris; Ryall, Jody; Spalteholz, Leo; Gooch, Amy; Douglas W. Cunningham and Gary Meyer and Laszlo Neumann
The discipline of graph visualization produces pictorial representations of node link structures. Much effort has been directed toward making such diagrams visually pleasing. A variety of aesthetic heuristics have been proposed, with the assumption that these will improve readability and understanding. We look at a perceptual basis for these heuristics, including Gestalt principles and Norman s emotional design framework. Next, we review the work to date on aesthetic heuristics and examine what has been done to evaluate these heuristics. We summarize this in a framework that outlines graph drawing heuristics, their perceptual basis, and evaluation status.
Aesthetics of Hand-Drawn vs. Computer-Generated Stippling
(The Eurographics Association, 2007) Maciejewski, Ross; Isenberg, Tobias; Andrews, William M.; Ebert, David S.; Sousa, Mario Costa; Douglas W. Cunningham and Gary Meyer and Laszlo Neumann
Recent work in non-photorealistic rendering has produced results comparable to hand-drawn artistic images. Inspiration for such techniques has come from many traditional artistic techniques, such as pen-and-ink, to depict tone, depth, and shape. These techniques can create visually appealing images and increase understanding as is evident in their use in medical textbooks, popular science, etc. However, when computer-generated images are visually compared to similar hand-drawn images, studies have shown that subjects are generally able to determine differences between both images. This seems to indicate that there are different aesthetics associated with computer-generated images and hand-drawn images. This paper discusses the implications of varying aesthetics amongst hand-drawn and computer-generated images, focusing particularly on the application of stippling to provide tone and shape to an image.
The Aesthetics of Rapidly-Exploring Random Trees
(ACM, 2013) Burch, Michael; Weiskopf, Daniel; Donald House and Cindy Grimm
Rapidly-Exploring Random Trees (RRTs) have been introduced as an algorithmic concept for the rapid exploration of configuration spaces targeting fast path planning, mainly applied in the field of robotics. Typically, such structured space organizations are only used on an algorithmic level but not for direct visual representation. In this paper, we illustrate the aesthetics of such RRTs by displaying them in a visual form that serves as a basis to generate algorithmic art. Apart from the visual encoding of such space-filling node-link diagrams, we demonstrate how these trees grow in the configuration space for RRT layouts with and without incremental distances from the initial point. Additionally, RRTs can be visually enhanced by several inherent tree metrics such as tree depth, subtree size, and branching factors to make the diagrams more aesthetically appealing and readable. We provide examples of different tree sizes and illustrate the effect of changes to several control parameters such as color coding, line segment thickness, layouts, and shape constraints.
The Aesthetics of the Underworld
(The Eurographics Association, 2008) Boukhelifa, Nadia; Duke, David J.; Douglas W. Cunningham and Victoria Interrante and Paul Brown and Jon McCormack
Although the development of computational aesthetics has largely concentrated on 3D geometry and illustrative rendering, aesthetics are equally an important principle underlying 2D graphics and information visualization. A canonical example is Beck's design of the London underground map, which not only produced an informative and practical artefact, but also established a design aesthetic that has been widely adopted in other applications. This paper contributes a novel hybrid view to the debate on aesthetics. It arises from a practical industrial problem, that of mapping the vast network of underground assets, and producing outputs that can be readily comprehended by a range of users, from back-office planning staff through to on-site excavation teams. This work describes the link between asset drawing aesthetics and tasks, and discusses methods developed to support the presentation of integrated asset data. It distinguishes a holistic approach to visual complexity, taking clutter as one component of aesthetics, from the graph-theoretic reductionist model needed to measure and remove clutter. We argue that ?de-cluttering' does not mean loss of information, but rather repackaging details to make them more accessible. In this respect, aesthetics have a fundamental role in implementing Schneiderman's mantra of 'overview, zoom & filter, details-on-demand' for information visualization.
The aMotion Toolkit: Painting with Affective Motion Textures
(The Eurographics Association, 2012) Lockyer, Matt; Bartram, Lyn; Douglas Cunningham and Donald House
Visual artists and designers frequently use carefully crafted motion textures patterns of ambient motion throughout a scene to imbue the atmosphere with affect. The design of such ambient visual cues is an elusive topic that has been studied by painters, theatre directors, scenic designers, lighting designers, filmmakers, producers, and artists for years. Recent research shows that such motion textures have the capacity to be both perceptually efficient and powerfully evocative, but adding them to scenes requires careful manipulation by hand : no tools currently exist to facilitate this integration. In this paper we describe the design and development of the aMotion toolkit: a palette of composable motion brushes for image and video based on our affective motion research. We discuss insights from an on-going qualitative study with professional visual effects de-signers into how such capabilities can enhance their current practice.
Animating Persian Floral Patterns
(The Eurographics Association, 2008) Etemad, Katayoon; Samavati, Faramarz F.; Prusinkiewicz, Przemyslaw; Douglas W. Cunningham and Victoria Interrante and Paul Brown and Jon McCormack
In this paper we describe Persian floral patterns and explore techniques for animating them. We present several approaches for this dynamic recreation: visualizing pattern symmetries, illustrating their design process, and simulating plant growth. For creating a pleasant illusion of a never-ending movie, we also explore an infinitely cycling effect for self-similar patterns. The construction of animating patterns is started by interactive modeling of plant elements using NURBS. We then use procedural techniques to control the animation.
Applications of High Precision Imaging Polarimetry
(The Eurographics Association, 2008) Neumann, Laszlo; Hegedus, Ramon; Horváth, Gábor; Garcia, Rafael; Douglas W. Cunningham and Victoria Interrante and Paul Brown and Jon McCormack
We propose the use of imaging polarimetry for general photography, which is a relatively young technique allowing the determination of polarized components of the light coming from extended objects or scenes. In this paper high resolution and accurate methods are introduced to determine the two linearly polarized components (Q;U) of light. The CIE Luv color space is used in this work to visualize the triplet of (I;Q;U) polarization image components. The structure of this color space is also highly appropriate to represent other attributes of linearly polarized light, such as the polarized intensity, degree and the angle of polarization. The accurately measured polarization components can also be efficiently used for image enhancement. In this direction, a new, polarization-based de-reflection method is proposed. This method is an optimal pixel-wise extension of the widely used photographical polarization filtering. Our method is also capable of amplifying the specular effects. Another application is de-hazing, which removes the linearly polarized component of the haze present in natural scenes, and results in a sharp and color-corrected image. Furthermore, the different combinations of visible and infrared polarization channels enable great possibilities in further de-hazing and to create artistic images.
Art Catalogue
(The Eurographics Association, 2008) different authors; Douglas W. Cunningham and Victoria Interrante and Paul Brown and Jon McCormack
Computational Aesthetics '08: Arts Programme
ARTcams: Attributed Rational Tensor Cameras
(The Eurographics Association, 2009) Li, Chuan; Hall, Peter; Willis, Philip; Oliver Deussen and Peter Hall
Non-linear camera models are playing an increasingly important role in computer graphics, especially in image based rendering and non-photorealistic rendering. We introduce ARTcams as simple non-linear cameras, which are unique in combining both geometric projection and non-geometric attributes such as colour into a single model. The geometric component of an ARTcam subsumes many contemporary non-linear cameras, including General Linear Cameras, push-broom cameras, and X-slit cameras. The colour component generalises compositing operations. ARTcams, though, by combining geometry and other attributes generalise yet further. ARTcams can be thought of as lenses (or mirrors) that can reproduce a wide variety of real effects, including aerial perspective, depth of field, as well as both geometric and chromatic aberrations. They can be calibrated for both geometry and colour against real optical devices. It is possible to specify ARTcams by drawing alone. This paper explains and demonstrates the ARTcam model.
Artistic Canvases for Gestural and Non-linear Typography
(The Eurographics Association, 2011) Kirton, Travis; Douglas Cunningham and Tobias Isenberg
This paper presents an exploration of gestural and non-linear typography through the production of two software applications, TextDraw and TypeIs. Both were created through a media-art-research practice, wherein extended periods of development and artistic practice were exclusive of one another. This approach yielded applications which challenge contemporary typesetting methodologies, and produced new artistic works which exemplify gestural and non-linear typesetting techniques. This paper discusses the development of both software applications, the artworks made possible through their use, and situates the work within a history of experimental western typography in the 20th century.
Arty Shapes
(The Eurographics Association, 2008) Song, Yi-Zhe; Rosin, Paul L.; Hall, Peter M.; Collomosse, John; Douglas W. Cunningham and Victoria Interrante and Paul Brown and Jon McCormack
This paper shows that shape simplification is a tool useful in Non-Photorealistic rendering from photographs, because it permits a level of abstraction otherwise unreachable. A variety of simple shapes (e.g. circles, triangles, squares, superellipses and so on) are optimally fitted to each region within a segmented photograph. The system automatically chooses the shape that best represents the region; the choice is made via a supervised classifier so the 'best shape' depends on the subjectivity of a user. The whole process is fully automatic, aside from the setting of two user variables to control the number of regions in a pair of segmentations - and even these can be left fixed for many images. A gallery of results shows how this work reaches towards the art of later Matisse, of Kandinsky, and other artists who favored shape simplification in their paintings.
Automated Landscape Painting in the Style of Bob Ross
(The Eurographics Association, 2009) Kalaidjian, Alex; Kaplan, Craig S.; Mann, Stephen; Oliver Deussen and Peter Hall
We present a system that can generate convincing synthetic landscape paintings with no user intervention whatsoever, nor any information about 3D geometry or lighting. The system is based on a direct implementation of the "wet-on-wet" oil painting technique taught by Bob Ross for many years on his show The Joy of Painting. We implement a canvas model and a set of brushes that correspond to the canvas and brushes that Bob Ross used on his show. We then compose brush strokes into landscape features that replicate his approach stroke by stroke. Finally, we develop an engine for automatic layout of these features in a painting. We demonstrate this automated system in the context of the Bob Ross painting Forest Hills.

Browse

Browsing Computational Aesthetics: EG Workshop on Computational Aesthetics in Graphics, Visualization and Imaging by Title

Results Per Page

Sort Options