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
    Benchmarking Non-Photorealistic Rendering of Portraits
    (Association for Computing Machinery, Inc (ACM), 2017) Rosin, Paul L.; Mould, David; Berger, Itamar; Collomosse, John; Lai, Yu-Kun; Li, Chuan; Li, Hua; Shamir, Ariel; Wand, Michael; Wang, Tinghuai; Winnem, Holger; Holger Winnemoeller and Lyn Bartram
    We present a set of images for helping NPR practitioners evaluate their image-based portrait stylisation algorithms. Using a standard set both facilitates comparisons with other methods and helps ensure that presented results are representative. We give two levels of di culty, each consisting of 20 images selected systematically so as to provide good coverage of several possible portrait characteristics. We applied three existing portraitspeci c stylisation algorithms, two generalpurpose stylisation algorithms, and one general learn ing based stylisation algorithm to the rst level of the benchmark, corresponding to the type of constrained images that have o ften been used in portraitspeci c work. We found that the existing methods are generally e ective on this new image set, demon strating that level one of the benchmark is tractable; challenges remain at level two. Results revealed several advantages conferred by portraitspeci c algorithms over generalpurpose algorithms: portraitspeci c algorithms can use domainspeci c information to preserve key details such as eyes and to eliminate extraneous details, and they have more scope for semantically meaningful abstraction due to the underlying face model. Finally, we pro vide some thoughts on systematically extending the benchmark to higher levels of di fficulty.
  • Item
    A generic framework for the structured abstraction of images
    (Association for Computing Machinery, Inc (ACM), 2017) Faraj, Noura; Xia, Gui-Song; Delon, Julie; Gousseau, Yann; Holger Winnemoeller and Lyn Bartram
    Structural properties are important clues for non-photorealistic representations of digital images. erefore, image analysis tools have been intensively used either to produce stroke-based render- ings or to yield abstractions of images. In this work, we propose to use a hierarchical and geometrical image representation, called a topographic map, made of shapes organized in a tree structure. ere are two main advantages of this analysis tool. Firstly, it is able to deal with all scales, so that every shape of the input image is represented. Secondly, it accounts for the inclusion properties within the image. By iteratively performing simple local operations on the shapes (removal, rotation, scaling, replacement. . . ), we are able to generate abstract renderings of digital photographs ranging from geometrical abstraction and painting-like e ects to style trans- fer, using the same framework. In particular, results show that it is possible to create abstract images evoking Malevitch's Suprematist school, while remaining grounded in the structure of digital images, by replacing all the shapes in the tree by simple geometric shapes.