Search Results

Now showing 1 - 10 of 11
  • Item
    Depth-aware Neural Style Transfer
    (Association for Computing Machinery, Inc (ACM), 2017) Liu, Xiao-Chang; Cheng, Ming-Ming; Lai, Yu-Kun; Rosin, Paul L.; Holger Winnemoeller and Lyn Bartram
    Neural style transfer has recently received signi cant a ention and demonstrated amazing results. An e cient solution proposed by Johnson et al. trains feed-forward convolutional neural networks by de ning and optimizing perceptual loss functions. Such methods are typically based on high-level features extracted from pre-trained neural networks, where the loss functions contain two components: style loss and content loss. However, such pre-trained networks are originally designed for object recognition, and hence the high-level features o en focus on the primary target and neglect other details. As a result, when input images contain multiple objects potentially at di erent depths, the resulting images are o en unsatisfactory because image layout is destroyed and the boundary between the foreground and background as well as di erent objects becomes obscured. We observe that the depth map e ectively re ects the spatial distribution in an image and preserving the depth map of the content image a er stylization helps produce an image that preserves its semantic content. In this paper, we introduce a novel approach for neural style transfer that integrates depth preservation as additional loss, preserving overall image layout while performing style transfer.
  • Item
    Real-Time Panorama Maps
    (Association for Computing Machinery, Inc (ACM), 2017) Brown, S. Alex; Samavati, Faramarz; Holger Winnemoeller and Lyn Bartram
    Panorama maps are stylized paintings of terrain often seen at tourist destinations. They are difficult to create since they are both artistic and grounded in real geographic data. In this paper we present techniques for rendering real-world data in the style of Heinrich Berann's panorama maps in a real-time application. We analyse several of Berann's paintings to identify the artistic elements used. We use this analysis to form algorithms that mimic the panorama map style, focusing on replicating the terrain deformation, distorted projection, terrain colouring, tree brush strokes, water rendering, and atmospheric scattering. In our approach we use freely available digital earth data to render interactive panorama maps without needing further design work.
  • 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
    Whole-Cloth Quilting Patterns from Photographs
    (Association for Computing Machinery, Inc (ACM), 2017) Liu, Chenxi; Hodgins, Jessica; McCann, James; Holger Winnemoeller and Lyn Bartram
    Whole-cloth quilts are decorative and functional artifacts made of plain cloth embellished with complicated stitching patterns. We describe a method that can automatically create a sewing pattern for a whole-cloth quilt from a photograph. Our technique begins with a segmented image, extracts desired and optional edges, and creates a continuous sewing path by approximately solving the Rural Postman Problem (RPP). In addition to many example quilts, we provide visual and numerical comparisons to previous single- line illustration approaches.
  • Item
    Quantifying Visual Abstraction ality for Stipple Drawings
    (Association for Computing Machinery, Inc (ACM), 2017) Spicker, Marc; Hahn, Franz; Lindemeier, Thomas; Saupe, Dietmar; Deussen, Oliver; Holger Winnemoeller and Lyn Bartram
    We investigate how the perceived abstraction quality of stipple illustrations is related to the number of points used to create them. Since it is di cult to nd objective functions that quantify the visual quality of such illustrations, we gather comparative data by a crowdsourcing user study and employ a paired comparison model to deduce absolute quality values. Based on this study we show that it is possible to predict the perceived quality of stippled representations based on the properties of an input image. Our results are related to Weber-Fechner's law from psychophysics and indicate a logarithmic relation between numbers of points and perceived abstraction quality. We give guidance for the number of stipple points that is typically enough to represent an input image well.
  • 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.
  • 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
    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.
  • 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.
  • Item
    Pigment-Based Recoloring of Watercolor Paintings
    (Association for Computing Machinery, Inc (ACM), 2017) Aharoni-Mack, Elad; Shambik, Yakov; Lischinski, Dani; Holger Winnemoeller and Lyn Bartram
    The color palette used by an artist when creating a painting is an important tool for expressing emotion, directing attention, and more. However, choosing a palette is an intricate task that requires considerable skill and experience. In this work, we introduce a new tool designed to allow artists to experiment with alternative color palettes for existing watercolor paintings. This could be useful for generating alternative renditions for an existing painting, or for aiding in the selection of a palette for a new painting, related to an existing one. Our tool first estimates the original pigment-based color palette used to create the painting, and then decomposes the painting into a collection of pigment channels, each corresponding to a single palette color. In both of these tasks, we employ a version of the Kubelka-Munk model, which predicts the reflectance of a given mixture of pigments. Each channel in the decomposition is a piecewise-smooth map that specifies the concentration of one of the colors in the palette across the image. Another estimated map specifies the total thickness of the pigments across the image. The mixture of these pigment channels, also according to the Kubelka- Munk model, reconstructs the original painting. The artist is then able to manipulate the individual palette colors, obtaining results by remixing the pigment channels at interactive rates.