CompAesth 05: Workshop on Computational Aesthetics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/321

Browse

Now showing 1 - 20 of 28

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.
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.
Benford's Law for Natural and Synthetic Images
(The Eurographics Association, 2005) Acebo, Esteve Del; Sbert, Mateu; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
Benford's Law (also known as the First Digit Law) is well known in statistics of natural phenomena. It states that, when dealing with quantities obtained from Nature, the frequency of appearance of each digit in the first significant place is logarithmic. This law has been observed over a broad range of statistical phenomena. In this paper, we will explore its application to image analysis. We will show how light intensities in natural images, under certain constraints, obey this law closely. We will also show how light intensities in synthetic images follow this law whenever they are generated using physically realistic methods, and fail otherwise. Finally, we will study how transformations on the images affect the adjustment to the Law and how the fitting to the law is related to the fitting of the distribution of the raw intensities of the image to a power law.
Breaking the Pixel Barrier
(The Eurographics Association, 2005) Isenberg, Tobias; Carpendale, M. Sheelagh T.; Sousa, Mario Costa; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
The majority of the current advances in computer graphic rendering strive for fast and realistic creation of pixel images, e. g., for the film and gaming industry. This development, unfortunately, leads to various problems due to limitations of pixel images, in particular, when they are not used for screen viewing. Thus, in this paper we argue for the placement of greater emphasis on the generation of vector graphics. Vector graphics offer the best approach for achieving effectiveness for both media simulation and illustration techniques. We discuss advantages of using vector graphics, pose a number of questions in this context, and evaluate directions of further research.
Color Search and Replace
(The Eurographics Association, 2005) Grundland, Mark; Dodgson, Neil A.; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
We present an interactive image enhancement technique to adjust the global color composition of an image by finding and replacing color gradients. We show how color gradient transformations can perform the basic operations of color editing. To recolor an image, the user designates a mapping of source color gradients to corresponding target color gradients. Each color gradient can be represented by a spherical parameterization, consisting of its midpoint color, contrast radius, as well as hue and luminance angles, in order to give the user separate and independent control over color shift, contrast adjustment, and color variation. Color gradients provide not only a flexible way of selecting color features but also a powerful way of manipulating image colors, as each mapping between a source and a target color gradient defines an affine color transformation. To determine the region of influence of each color mapping, perceptual similarity between colors is evaluated by applying Shepard s law of generalization to color differences. Through a feature-based warping approach, our color warping algorithm applies a continuous, nonlinear, volumetric deformation to the color space in order to approximate the requested color mappings. By making interactive color correction easier to control, our technique may prove useful in a variety of color image enhancement tasks in digital photography, video processing, and information visualization.
Color Style Transfer Techniques using Hue, Lightness and Saturation Histogram Matching
(The Eurographics Association, 2005) Neumann, Attila; Neumann, László; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
We present new methods which transfer the color style of a source image into an arbitrary given target image having a different 3D color distribution. The color transfer has a high importance ensuring a wide area of applications from artistic transformation of the color atmosphere of images until different scientific visualizations using special gamut mappings. Our technique use a permissive, or optionally strict, 3D histogram matching, similarly to the sampling of multivariable functions applying a sequential chain of conditional probability density functions. We work by order of hue, hue dependent lightness and from both dependent saturation histograms of source and target images, respectively. We apply different histogram transformations, like smoothing or contrast limitation, in order to avoid some unexpected high gradients and other artifacts. Furthermore, we use dominance suppression optionally, by applying sub-linear functions for the histograms in order to get well balanced color distributions, or an overall appearance reflecting the memory color distribution better. Forward and inverse operations on the corresponding cumulative histograms ensure a continuous mapping of perceptual attributes correlating to limited derivatives. Sampling an appropriate fraction of the pixels and using perceptually accurate and continuous histograms with minimal size as well as other gems make this method robust and fast.
Computational Automotive Color Appearance
(The Eurographics Association, 2005) Meyer, Gary W.; Shimizu, Clement; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
A computer graphic system has been developed that permits the interactive design of new automotive finishes. The software makes use of a reflection model for car paint that is based on industry standards for measuring the appearance characteristics of the paint. These measurements include gloss for the clearcoat and three aspecular measurements for the metallic basecoat. The program interface provides a means for altering the reflectance properties of the paint and for visualizing the effect of those changes on the color appearance of the car. The desired aspecular measurements for the new paint can be input to a paint formulation system so that the paint can be manufactured. A test of the system shows good correspondence between the designed and the fabricated paint.
Computational Color Harmony based on Coloroid System
(The Eurographics Association, 2005) Neumann, László; Nemcsics, Antal; Neumann, Attila; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
This paper presents experimentally based rules and methods for the creation of harmonic color sets. First, dichromatic rules are presented which concern the harmony relationships of two hues. For an arbitrarily given hue pair, we define the just harmonic saturation values, resulting in minimally harmonic color pairs. These values express the fuzzy border between harmony and disharmony regions using a single scalar. Second, the value of harmony is defined corresponding to the contrast of lightness, i.e. the difference of perceptual lightness values. Third, we formulate the harmony value of the saturation contrast, depending on hue and lightness. The results of these investigations form a basis for a unified, coherent dichromatic harmony formula as well as for analysis of polychromatic color harmony. Introduced color harmony rules are based on Coloroid, which is one of the 5 - 6 main color-order systems and furthermore it is an aesthetically uniform continuous color space. Coloroid has simple closed forward and backward transformation formulas with the color space of CIE XYZ. It relies on a huge number of observations and experiments, and it is a very suitable tool of color dynamics for describing aesthetical relationships. It has been used in numerous architectural projects. The experimental data that may be retrieved from them are only partly processed and published so far. Our article utilizes a 'slice' of this database, together with additional complementary observations. This paper is the first of a planned series of articles, dealing with rules and coherences of color harmony based on the Coloroid system.
Computer Aided Color Appearance Design using Environment Map Based Lighting
(The Eurographics Association, 2005) Shimizu, Clement; Meyer, Gary W.; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
A BRDF approximation is developed that is suitable for interactive color appearance design in direct lighting provided by environment maps. The BRDFs are approximated as a linear combination of cosine lobes with a fixed set of specular exponents. A nonlinear optimization routine is used to fit the cosine lobes to BRDFs appropriate for a specific color appearance design application: automotive paint. Modification and rendering of the BRDF is made possible by linearly combining prefiltered environment maps for each cosine lobe in real time.
Computer Generated Stereoscopic Artwork
(The Eurographics Association, 2005) Stavrakis, Stathis; Gelautz, Margrit; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
The focus of this work is to investigate and simulate artistic techniques in stereoscopy that go beyond stereo photography, such as stereoscopic painting. We briefly discuss the topic from a stereo artist s perspective and map some of our observations from traditional stereo techniques to the scientific domain, where we use them to tackle technical tasks involved in the generation of stereo artwork. We describe a framework that we use in our stereoscopic image-based non-photorealistic rendering algorithms, but it can be adopted by other single-view artistic image synthesis techniques in order to generate stereoscopic output.
Defining Computational Aesthetics
(The Eurographics Association, 2005) Hoenig, Florian; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
This paper attempts to define the discipline of Computational Aesthetics in the context of computer science, partly reflecting the contributions and comprehensive discussions of the first EG Workshop on Computational Aesthetics in Graphics, Visualization and Imaging. It points out the current problem of "aesthetic pollution" as a side effect of computer aided design and gives motivation to improve current computational methods by adding aesthetic awareness. An introduction on how this could be achieved is given, listing significant results of previous research. It turned out that there are factors of aesthetics such as complexity and order, that could add up to a working measure. For building a pragmatic view on such measures, very restrictive scenarios of application are given. To conclude, the major aspects of this new discipline are stressed. They are (1) developing computational methods for aesthetic decisions, (2) taking human perception into account and (3) focusing on aesthetics in form and particularly objects of design, in order to guarantee immediate application.
Designing Metrics for the Purpose of Aesthetically Evaluating
(The Eurographics Association, 2005) Greenfield, Gary R.; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
The algorithmic and evolutionary art movements within computer-generated art have helped spur interest in evaluating images on the basis of their aesthetic merit. When attempting to use non-interactive techniques to address this issue, two problems arise: (1) designing metrics that have explicit computational representations, and (2) establishing that such metrics actually fulfill their intended purpose. We survey our experiences in designing metrics for non-interactively guiding image evolution to obtain aesthetic images and we propose a taxonomy for metric frameworks. We also discuss some issues relevant to validating such metrics.
Enhancing Perceived Depth in Images Via Artistic Matting
(The Eurographics Association, 2005) Gooch, Amy A.; Gooch, Bruce; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
We present an algorithm for the addition of artistic mattes to digital images for the purpose of enhancing the sense of depth in the image. We provide examples exploring color and double mattes as well as report the results from a perception study which may indicate an increase in perceived depth in matted imagery.
Fast Techniques for Mosaic Rendering
(The Eurographics Association, 2005) DiBlasi, G.; Gallo, G.; Petralia, M.; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
Art often provides valuable hints for technological innovations especially in the field of Image Processing and Computer Graphics. In this paper we survey in an unified framework three methods to transform a raster input image into good quality mosaics: artificial mosaic, photomosaic and puz zle image mosaic. The common and different ideas among these methods are reported. The main goal of all the methods is to produce good results in an acceptable time and without user intervention. Examples reported in the paper show how the right mixture of mathematical tools may lead to impressive results.
Form Follows Function: Aesthetic Interactive Labels
(The Eurographics Association, 2005) Götzelmann, Timo; Ali, Kamran; Hartmann, Knut; Strothotte, Thomas; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
Labels effectively convey co-referential relations between textual and visual elements and are a powerful tool to support learning tasks. Therefore, almost all illustrations in scientific or technical documents employ a large number of labels. This paper introduces a novel approach to integrate internal and external labels into projections of complex 3D models in the fashion of hand-made illustrations. The real-time label layout algorithms proposed in the paper balance a number of conflicting requirements such as unambiguity, readability, aesthetic considerations and frame-coherency.
A Generative Model For Dynamic Canvas Motion
(The Eurographics Association, 2005) Kaplan, Matthew; Cohen, Elaine; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
We present techniques for constructing realistic canvas and paper models and for enabling interactive dynamic canvas motion. Dynamic canvas motion means that there is a correspondence between the motion of canvas features and the motion of the models in the scene. Our artificial paper is created by simulating the physical process of creating paper with many individual fibers. To enable canvas motion, fibers are associated with each of the models in the scene. At runtime, the fibers associated with visible portions of the models and background fibers are used to construct a 2D canvas. Because fibers are "tied" to the models, the motion of canvas features corresponds to the motion of each model. This allows us to match the motion field of our dynamic 2D canvas to that of the the 3D scene exactly.
Global Contrast Factor - a New Approach to Image Contrast
(The Eurographics Association, 2005) Matkovic, Kresimir; Neumann, László; Neumann, Attila; Psik, Thomas; Purgathofer, Werner; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
Contrast in image processing is usually defined as a ratio between the darkest and the brightest spots of an image. In this paper we introduce a different contrast definition. The newly introduced Global Contrast Factor (GCF) corresponds closer to the human perception of contrast. GCF uses contrasts at various resolution levels in order to compute overall contrast. Experiments were conducted in order to find weight factors needed to calculate GCF. GCF measures richness of detail as perceived by a human observer, and as such can be used in various application areas like rendering, tone mapping, volume visualization, and lighting design.
Illustrative Scientific Visualization Framework
(The Eurographics Association, 2005) Sousa, Mario Costa; Gooch, Amy Ashurst; Gooch, Bruce; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
Current scientific visualization techniques create complex images that may be difficult to interpret and do not have the expressiveness of illustrations. Incorporating traditional scientific illustration techniques into a visualization system enables artists and non-artists to harnesses the power of traditional illustration techniques when visually representing scientific data. In this paper we present an illustrative scientific visualization framework incorporating general illustration principles, as well as techniques and aesthetics of various styles. Such a framework provides a basic foundation for categorizing and communicating research and may stimulate future illustrative visualization systems.
Illustrative Visualization for Medical Training
(The Eurographics Association, 2005) Sousa, Mario Costa; Ebert, David S.; Stredney, Don; Svakhine, Nikolai A.; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
A system is presented that produces images that simulate pictorial representations for both scientific and biomedical visualization. It combines traditional and novel volume illustration techniques. We present examples to distill representational techniques for both creative exploration and emphatic presentation for clarity. More specifically, we present adaptations of these techniques for interactive simulation sessions being developed in a concurrent project for resident training in temporal bone dissection simulation. The goal of this effort is to evaluate the use of emphatic rendering to guide the user in an interactive session and to facilitate the learning of complex biomedical information, including structural, functional, and procedural information.
An Information-Theoretic Framework for Image Complexity
(The Eurographics Association, 2005) Rigau, Jaume; Feixas, Miquel; Sbert, Mateu; Laszlo Neumann and Mateu Sbert and Bruce Gooch and Werner Purgathofer
In this paper, we introduce a new information-theoretic approach to study the complexity of an image. The new framework we present here is based on considering the information channel that goes from the histogram to the regions of the partitioned image, maximizing the mutual information. Image complexity has been related to the entropy of the image intensity histogram. This disregards the spatial distribution of pixels, as well as the fact that a complexity measure must take into account at what level one wants to describe an object. We define the complexity by using two measures which take into account the level at which the image is considered. One is the number of partitioning regions needed to extract a given ratio of information from the image. The other is the compositional complexity given by the Jensen-Shannon divergence of the partitioned image.

Browse

Browsing CompAesth 05: Workshop on Computational Aesthetics by Title

Results Per Page

Sort Options