Search Results

Now showing 1 - 3 of 3
  • Item
    Neural Style Transfer: A Paradigm Shift for Image-based Artistic Rendering?
    (Association for Computing Machinery, Inc (ACM), 2017) Semmo, Amir; Isenberg, Tobias; Döllner, Jürgen; Holger Winnemoeller and Lyn Bartram
    In this meta paper we discussimage-based artistic rendering (IB-AR)based onneural style transfer(NST) and argue, while NST may represent a paradigm shift for IB-AR, that it also has to evolve as an interactive tool that considers the design aspects and mecha- nisms of artwork production. IB-AR received signifficant attention in the past decades for visual communication, covering a plethora of techniques to mimic the appeal of artistic media. Example-based renderingrepresents one the most promising paradigms in IB-AR to (semi-)automatically simulate artistic media with high fidelity, but so far has been limited because it relies on pre-defined image pairs for training or informs only low-level image features for texture transfers. Advancements in deep learning showed to alleviate these limitations by matching content and style statistics via activations of neural network layers, thus making a generalized style trans- fer practicable. We categorize style transfers within the taxonomy of IB-AR, then propose a semiotic structure to derive a technical research agenda for NSTs with respect to the grand challenges of NPAR. We finally discuss the potentials of NSTs, thereby identifying applications such as casual creativity and art production.
  • Item
    Interactive NPAR: What Type of Tools Should We Create?
    (The Eurographics Association, 2016) Isenberg, Tobias; Pierre Bénard and Holger Winnemöller
    I argue that we need to increase our consideration of the interaction that is possible and/or needed for the NPAR algorithms we develop. Depending on the application domain of a given algorithmic contribution, different degrees of interaction are required to make it practically useful and, thus, relevant. The spectrum of interactivity ranges from (almost) fully automatic processing to levels of control that are similar to those of traditional tools-some of the approaches even needing to support the full spectrum. Only if these considerations are first-class members of the NPAR development process can we expect others to want to work with our tools and to use them on a regular basis.
  • Item
    Drawing Characteristics for Reproducing Traditional Hand-Made Stippling
    (The Eurographics Association, 2015) Martín, Domingo; Sol, Vicente del; Romo, Celia; Isenberg, Tobias; David Mould and Pierre Bénard
    We contribute an in-depth analysis of the characteristics of traditional stippling and relate these to common practices in NPAR stippling techniques as well as to the abilities and limitations of existing printing and display technology. In our work we focus specifically on the properties of stipple dots and consider the dimensions and attributes of pens and paper types used in artistic practice. With our analysis we work toward an understanding of the requirements for digital stippling, with the ultimate goal to provide tools to artists and illustrators that can replicate the stippling process faithfully in the digital domain. From the results of our study we provide a dataset for use in new example-based stippling techniques, derive a taxonomy of characteristics and conditions for the reproduction of stippling, and define future directions of work.