CompAesth 17: Workshop on Computational Aesthetics

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2631839

Browse

Browsing CompAesth 17: Workshop on Computational Aesthetics by Subject "Computing methodologies Non"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Detail and Color Enhancement in Photo Stylization
    (Association for Computing Machinery, Inc (ACM), 2017) Azami, Rosa; Mould, David; Holger Winnemoeller and Lyn Bartram
    Abstraction in non-photorealistic rendering reduces the amount of detail, yet non-essential details can improve visual interest and thus make an image more appealing. In this paper, we propose an automatic system for photo manipulation that brightens an image and alters the detail levels. The process first applies an edgepreserving abstraction process to an input image, then uses the residual to reintroduce and exaggerate details in areas near strong edges. At the same time, image regions further from strong edges are brightened. The final result is a lively mixture of abstraction and enhanced detail.
  • Thumbnail Image
    Item
    Organized Order in Ornamentation
    (Association for Computing Machinery, Inc (ACM), 2017) Gieseke, Lena; Asente, Paul; Lu, Jingwan; Fuchs, Martin; Holger Winnemoeller and Lyn Bartram
    Decorative ornamentation involves a careful balance between accent and order. Existing techniques leave artists either with tedious manual processes or the uncontrolled automatic generation of rather homogeneous patterns that lack creatively-placed visual highlights. We present a method to close this gap, offering the control and quality of manual creation, and the effciency and accuracy of computation. At the core of our system, customizable and modularly combinable element placement functions fill a space automatically under global design constraints. We provide a set of example placement functions that implement order based on design principles for ornamentation such as balanced element distribution and symmetry. To create structural hierarchies and to guide an ornament to the space it fills, we allow artists to direct the connectivity of elements with drawn strokes. Artists can also draw guides to create vector fields, which organize the ornament along streamlines. Path planning automatically routes around obstacles while aligning the ornament to their borders. Our method combines high-level control mechanisms like taking guidance from example images to low-level control like placing single elements as visual accents and making local edits within the computed ornament. By automating tedious tasks and offering familiar input mechanisms like drawing, we enable artists to focus on the creative intent.
  • Thumbnail Image
    Item
    Shading with Painterly Filtered Layers: A Technique to Obtain Painterly Portrait Animations
    (Association for Computing Machinery, Inc (ACM), 2017) Castaneda, Saif; Akleman, Ergun; Holger Winnemoeller and Lyn Bartram
    In this manuscript, we describe a process that can be used to create still and/or animated portrait paintings to be shown in Expressive Art Exhibit. Our process consists of two stages: (1) Creation of control textures for a Barycentric shader by using color information gathered from photographs to provide realistic looking skin rendering; (2) Filtering and compositing the layers of images that are obtained by control textures, which correspond to effects such as diffuse, specular and ambient. To demonstrate proof-of-concept, we have created a few rigid body animations of painterly portraits under different lighting conditions.