Conventional digital painting systems rely on procedural rules and physical simulation to render paint strokes. We present an interactive, data-driven painting system that uses scanned images of real natural media to synthesize both new strokes and complex stroke interactions, obviating the need for physical simulation. First, users capture images of real media, including examples of isolated strokes, pairs of overlapping strokes, and smudged strokes. Online, the user inputs a new stroke path, and our system synthesizes its 2D texture appearance with optional smearing or smudging when strokes overlap. We demonstrate high-fidelity paintings that closely resemble the captured media style, and also quantitatively evaluate our synthesis quality via user studies.

RealBrush: painting with examples of physical media

Camouflage images contain one or more hidden figures that remain imperceptible or unnoticed for a while. In one possible explanation, the ability to delay the perception of the hidden figures is attributed to the theory that human perception works in two main phases: feature search and conjunction search. Effective camouflage images make feature based recognition difficult, and thus force the recognition process to employ conjunction search, which takes considerable effort and time. In this paper, we present a technique for creating camouflage images. To foil the feature search, we remove the original subtle texture details of the hidden figures and replace them by that of the surrounding apparent image. To leave an appropriate degree of clues for the conjunction search, we compute and assign new tones to regions in the embedded figures by performing an optimization between two conflicting terms, which we call immersion and standout, corresponding to hiding and leaving clues, respectively. We show a large number of camouflage images generated by our technique, with or without user guidance. We have tested the quality of the images in an extensive user study, showing a good control of the difficulty levels.

Camouflage images

In this meta paper we discuss image-based artistic rendering (IB-AR) based on neural 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 mechanisms of artwork production IB-AR received significant attention in the past decades for visual communication, covering a plethora of techniques to mimic the appeal of artistic media Example-based rendering represents 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 transfer 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

/pdf/neural-style-transfer-a-paradigm-shift-for-image-based-59rk47ksfm.pdf

Neural style transfer: a paradigm shift for image-based artistic rendering?

In this publication we will look at the different methods presented over the past few decades which attempt to recreate digital paintings. While previous surveys concentrate on the broader subject of non-photorealistic rendering, the focus of this paper is firmly placed on painterly rendering techniques. We compare different methods used to produce different output painting styles such as abstract, colour pencil, watercolour, oriental, oil and pastel. Whereas some methods demand a high level of interaction using a skilled artist, others require simple parameters provided by a user with little or no artistic experience. Many methods attempt to provide more automation with the use of varying forms of reference data. This reference data can range from still photographs, video, 3D polygonal meshes or even 3D point clouds. The techniques presented here endeavour to provide tools and styles that are not traditionally available to an artist. Copyright © 2012 John Wiley & Sons, Ltd.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/cav.1435

Painterly rendering techniques: a state‐of‐the‐art review of current approaches

We introduce a novel technique to generate painterly art maps (PAMs) for 3D nonphotorealistic rendering. Our technique can automatically transfer brushstroke textures and color changes to 3D models from samples of a painted image. Therefore, the generation of stylized images or animation in the style of a given artwork can be achieved. This new approach works particularly well for a rich variety of brushstrokes ranging from simple 1D and 2D line-art strokes to very complicated ones with significant variations in stroke characteristics. During the rendering or animation process, the coherence of brushstroke textures and color changes over 3D surfaces can be well maintained. With PAM, we can also easily generate the illusion of flow animation over a 3D surface to convey the shape of a model.

/pdf/stylized-rendering-using-samples-of-a-painted-image-4b62mycxi5.pdf

Stylized Rendering Using Samples of a Painted Image

A nonphotorealistic rendering (NPR) technique can help medical practitioners visualize anatomic models and illustrate them with different stylizations. This technique provides potentially useful rendering alternatives to conventional volume or surface rendering in medical visualization. Improved performance allows interactive visualization of anatomic models, and additional stroke texture synthesis enriches medical object illustrations

Stylized Rendering for Anatomic Visualization

We introduce a new method for texture synthesis on regular and irregular example textures. In this paper, an enhanced patch-based algorithm is proposed to select patches with the best structural similarity and to avoid discontinuity at the boundary of adjacent patches. This new method utilizes a feature-weighted function to measure the structural similarity. A re-synthesis technique is presented to reduce the structural discontinuity. We conduct a comparison study to verify the proposed method. Preliminary experiments show that the proposed method can yield better results than other well-known methods for examples used in this study.

Feature-Based texture synthesis

We present a novel method for multiresolution remeshing of irregular mesh. First, the original mesh (two-manifold any genus) is decomposed into several patches, each patch is homeomorphic to a 2D triangle. The goal of this decomposition process is that the decomposed patches are size-equally. First, a mesh is manually cut into a few disk-like patches. With the help of weighted centroidal Voronoi diagram (WCVD), each patch is then automatically partitioned into more triangular patches with nearly equal size. Recursively subdividing these triangular patches, we finally get a semi-regular mesh.

/pdf/multiresolution-remeshing-using-weighted-centroidal-voronoi-2i7dfujhcm.pdf

Multiresolution remeshing using weighted centroidal voronoi diagram

In this paper, we propose a new patch-based texture synthesis method. The proposed method consists of two main components: a feature-weighted similarity and a pixel-based re-synthesis step. Most existing patch-based methods can only handle for frontal-parallel textures (FPT) and generate poorly synthesized results for non-frontal-parallel textures (NFPT). To better synthesize NFPT, we enhance the proposed method with a view warping technique. As a result, the proposed method can handle well for FPT and NFPT

Chung-Ren Yan

Papers

Stylized Rendering Using Samples of a Painted Image

Stylized Rendering for Anatomic Visualization

Feature-Based texture synthesis

Multiresolution remeshing using weighted centroidal voronoi diagram

Patch-Based Synthesis for Non-frontal-parallel Textures (NFPT)