NPAR: Non-Photorealistic Animation and Rendering

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/990

Browse

Now showing 1 - 20 of 42

Active Strokes: Coherent Line Stylization for Animated 3D Models
(The Eurographics Association, 2012) Benard, Pierre; Lu, Jingwan; Cole, Forrester; Finkelstein, Adam; Thollot, Joelle; Paul Asente and Cindy Grimm
This paper presents a method for creating coherently animated line drawings that include strong abstraction and stylization effects. These effects are achieved with active strokes: 2D contours that approximate and track the lines of an animated 3D scene. Active strokes perform two functions: they connect and smooth unorganized line samples, and they carry coherent parameterization to support stylized rendering. Line samples are approximated and tracked using active contours (''snakes'') that automatically update their arrangment and topology to match the animation. Parameterization is maintained by brush paths that follow the snakes but are independent, permitting substantial shape abstraction without compromising fidelity in tracking. This approach renders complex models in a wide range of styles at interactive rates, making it suitable for applications like games and interactive illustrations.
Art-directed Watercolor Rendered Animation
(The Eurographics Association, 2016) Montesdeoca, Santiago E.; Seah, Hock-Soon; Rall, Hans-Martin; Pierre Bénard and Holger Winnemöller
This paper presents a system to render 3D animated geometry as watercolor painted animation with art-directed control. Our approach focuses on letting the end user paint the influence of the modeled watercolor effects in the 3D scene to simulate the characteristic appearance of traditional watercolor. For this purpose, it performs an object-space simulation and makes use of the user-painted influences to control and enhance image-space watercolor effects. In contrast to previous approaches, we introduce specialized watercolor shaders that are adjusted and deformed according to the desired painted effects. We further present novel algorithms that simulate hand tremors, pigment turbulence, color bleeding, edge darkening, paper distortion and granulation. All of these represent essential characteristic effects of traditional watercolor. The system performs in real-time, scales well with scene complexity and is fully implemented in Autodesk Maya.
Automatic Texture Guided Color Transfer and Colorization
(The Eurographics Association, 2016) Arbelot, Benoit; Vergne, Romain; Hurtut, Thomas; Thollot, Joëlle; Pierre Bénard and Holger Winnemöller
This paper targets two related color manipulation problems: Color transfer for modifying an image's colors and colorization for adding colors to a grayscale image. Automatic methods for these two applications propose to modify the input image using a reference that contains the desired colors. Previous approaches usually do not target both applications and suffer from two main limitations: possible misleading associations between input and reference regions and poor spatial coherence around image structures. In this paper, we propose a unified framework that uses the textural content of the images to guide the color transfer and colorization. Our method introduces an edge-aware texture descriptor based on region covariance, allowing for local color transformations. We show that our approach is able to produce results comparable or better than state-of-the-art methods in both applications.
A Benchmark Image Set for Evaluating Stylization
(The Eurographics Association, 2016) Mould, David; Rosin, Paul L.; Pierre Bénard and Holger Winnemöller
The non-photorealistic rendering community has had difficulty evaluating its research results. Other areas of computer graphics, and related disciplines such as computer vision, have made progress by comparing algorithms' performance on common datasets, or benchmarks. We argue for the benefits of establishing a benchmark image set to which image stylization methods can be applied, simplifying the comparison of methods, and broadening the testing to which a given method is subjected. We propose a preliminary set of benchmark images, representing a range of possible subject matter and image features of interest to researchers, and we describe the policies, tradeoffs, and reasoning that led us to the particular images in the set.
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.
Characterizing User Behavior for Speech and Sketch-based Video Retrieval Interfaces
(Association for Computing Machinery, Inc (ACM), 2017) Altıok, Ozan Can; Sezgin, Tev k Metin; Holger Winnemoeller and Lyn Bartram
From a user interaction perspective, speech and sketching make a good couple for describing motion. Speech allows easy speci cation of content, events and relationships, while sketching brings in spatial expressiveness. Yet, we have insu cient knowledge of how sketching and speech can be used for motionbased video retrieval, because there are no existing retrieval systems that support such interaction. In this paper, we describe a WizardofOz protocol and a set of tools that we have developed to engage users in a sketch and speechbased video retrieval task. We report how the tools and the protocol t together using ''retrieval of soccer videos'' as a use case scenario. Our so ware is highly customizable, and our protocol is easy to follow. We believe that together they will serve as a convenient and powerful duo for studying a wide range of multimodal use cases.
Combining Sketch and Tone for Pencil Drawing Production
(The Eurographics Association, 2012) Lu, Cewu; Xu, Li; Jia, Jiaya; Paul Asente and Cindy Grimm
We propose a new system to produce pencil drawing from natural images. The results contain various natural strokes and patterns, and are structurally representative. They are accomplished by novelly combining the tone and stroke structures, which complement each other in generating visually constrained results. Prior knowledge on pencil drawing is also incorporated, making the two basic functions robust against noise, strong texture, and significant illumination variation. In light of edge, shadow, and shading information conveyance, our pencil drawing system establishes a style that artists use to understand visual data and draw them. Meanwhile, it lets the results contain rich and well-ordered lines to vividly express the original scene.
Consistent Stylization and Painterly Rendering of Stereoscopic 3D Images
(The Eurographics Association, 2012) Northam, Lesley; Asente, Paul; Kaplan, Craig S.; Paul Asente and Cindy Grimm
We present a method for stylizing stereoscopic 3D images that guarantees consistency between the left and right views. Our method decomposes the left and right views of an input image into discretized disparity layers and merges the corresponding layers from the left and right views into a single layer where stylization takes place. We then construct new stylized left and right views by compositing portions of the stylized layers. Because the left and right views come from the same source layers, our method eliminates common artifacts that cause viewer discomfort. We also present a stereoscopic 3D painterly rendering algorithm tailored to our layerbased approach. This method uses disparity information to assist in stroke creation so that strokes follow surface geometry without ignoring painted surface patterns. Finally, we conduct a user study that demonstrates that our approach to stereoscopic 3D image stylization leads to images that are more comfortable to view than those created using other techniques.
Data-Driven Iconification
(The Eurographics Association, 2016) Liu, Yiming; Agarwala, Aseem; Lu, Jingwan; Rusinkiewicz, Szymon; Pierre Bénard and Holger Winnemöller
Pictograms (icons) are ubiquitous in visual communication, but creating the best icon is not easy: users may wish to see a variety of possibilities before settling on a final form, and they might lack the ability to draw attractive and effective pictograms by themselves. We describe a system that synthesizes novel pictograms by remixing portions of icons retrieved from a large online repository. Depending on the user's needs, the synthesis can be controlled by a number of interfaces ranging from sketch-based modeling and editing to fully-automatic hybrid generation and scribble-guided montage. Our system combines icon-specific algorithms for salient-region detection, shape matching, and multi-label graph-cut stitching to produce results in styles ranging from line drawings to solid shapes with interior structure.
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.
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.
Edge- and substrate-based effects for watercolor stylization
(Association for Computing Machinery, Inc (ACM), 2017) Montesdeoca, Santiago E.; Seah, Hock Soon; Bénard, Pierre; Vergne, Romain; Thollot, Joëlle; Rall, Hans-Martin; Benvenuti, Davide; Holger Winnemoeller and Lyn Bartram
We investigate characteristic edge- and substrate-based effects for watercolor stylization. These two fundamental elements of painted art play a significant role in traditional watercolors and highly influence the pigment's behavior and application. Yet a detailed consideration of these specific elements for the stylization of 3D scenes has not been attempted before. Through this investigation, we contribute to the field by presenting ways to emulate two novel effects: dry-brush and gaps & overlaps. By doing so, we also found ways to improve upon well-studied watercolor effects such as edge- darkening and substrate granulation. Finally, we integrated con- trollable external lighting influences over the watercolorized result, together with other previously researched watercolor effects. These effects are combined through a direct stylization pipeline to produce sophisticated watercolor imagery, which retains spatial coherence in object-space and is locally controllable in real-time.
ELASTIFACE: Matching and Blending Textured Faces
(ACM, 2013) Zell, Eduard; Botsch, Mario; Forrester Cole and Cindy Grimm
In this paper we present ELASTIFACE, a simple and versatile method for establishing correspondence between textured face models, either for the construction of a blend-shape facial rig or for the exploration of new characters by morphing between a set of input models. While there exists a wide variety of approaches for inter-surface mapping and mesh morphing, most techniques are not suitable for our application: They either require the insertion of additional vertices, are limited to topological planes or spheres, are restricted to near-isometric input meshes, and/or are algorithmically and computationally involved. In contrast, our method extends linear non-rigid registration techniques to allow for strongly varying input geometries. It is geometrically intuitive, simple to implement, computationally efficient, and robustly handles highly non-isometric input models. In order to match the requirements of other applications, such as recent perception studies, we further extend our geometric matching to the matching of input textures and morphing of geometries and rendering styles.
Example-Based Brushes for Coherent Stylized Renderings
(Association for Computing Machinery, Inc (ACM), 2017) Zheng, Ming; Milliez, Antoine; Gross, Markus; Sumner, Robert W.; Holger Winnemoeller and Lyn Bartram
Painterly stylization is the cornerstone of non-photorealistic render- ing. Inspired by the versatility of paint as a physical medium, exist- ing methods target intuitive interfaces that mimic physical brushes, providing artists the ability to intuitively place paint strokes in a digital scene. Other work focuses on physical simulation of the interaction between paint and paper or realistic rendering of wet and dry paint. In our work, we leverage the versatility of example- based methods that can generate paint strokes of arbitrary shape and style based on a collection of images acquired from physical media. Such ideas have gained popularity since they do not require cumbersome physical simulation and achieve high fidelity without the need of a specific model or rule set. However, existing methods are limited to the generation of static 2D paintings and cannot be applied in the context of 3D painting and animation where paint strokes change shape and length as the camera viewport moves. Our method targets this shortcoming by generating temporally- coherent example-based paint strokes that accommodate to such length and shape changes. We demonstrate the robustness of our method with a 2D painting application that provides immediate feedback to the user and show how our brush model can be ap- plied to the screen-space rendering of 3D paintings on a variety of examples.
Front- and Backmatter: NPAR 2017
(Association for Computing Machinery, Inc (ACM), 2017) Holger Winnemoeller; Lyn Bartram; Holger Winnemoeller and Lyn Bartram
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.
Hybrid-Space Localized Stylization Method for View-Dependent Lines Extracted from 3D Models
(The Eurographics Association, 2015) Cardona, Luis; Saito, Suguru; David Mould and Pierre Bénard
We propose a localized stylization method that combines object-space and image-space techniques to locally styl- ize view-dependent lines extracted from 3D models. In the input phase, the user can customize a style and draw strokes by tracing over view-dependent feature lines such as occluding contours and suggestive contours. For each stroke drawn, the system stores its style properties as well as its surface location on the underlying polygonal mesh as a data structure referred as registered stroke. In the rendering phase, a new attraction field leads active contours generated from the registered strokes to match current frame feature lines and maintain the style and path coordinates of strokes in nearby viewpoints. For each registered stroke, a limited surface region referred as influence area is used to improve the line matching accuracy and discard obvious mismatches. The proposed styl- ization system produces uncluttered line drawings that convey additional information such as material properties or feature sharpness and is evaluated by measuring its usability and performance.
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.
Map Style Formalization: Rendering Techniques Extension for Cartography
(The Eurographics Association, 2016) Christophe, Sidonie; Duménieu, Bertrand; Turbet, Jérémie; Hoarau, Charlotte; Mellado, Nicolas; Ory, Jérémie; Loi, Hugo; Masse, Antoine; Arbelot, Benoit; Vergne, Romain; Brédif, Mathieu; Hurtut, Thomas; Thollot, Joëlle; Vanderhaeghe, David; Pierre Bénard and Holger Winnemöller
Cartographic design requires controllable methods and tools to produce maps that are adapted to users' needs and preferences. The formalized rules and constraints for cartographic representation come mainly from the conceptual framework of graphic semiology. Most current Geographical Information Systems (GIS) rely on the Styled Layer Descriptor and Semiology Encoding (SLD/SE) specifications which provide an XML schema describing the styling rules to be applied on geographic data to draw a map. Although this formalism is relevant for most usages in cartography, it fails to describe complex cartographic and artistic styles. In order to overcome these limitations, we propose an extension of the existing SLD/SE specifications to manage extended map stylizations, by the means of controllable expressive methods. Inspired by artistic and cartographic sources (Cassini maps, mountain maps, artistic movements, etc.), we propose to integrate into our system three main expressive methods: linear stylization, patch-based region filling and vector texture generation. We demonstrate how our pipeline allows to personalize map rendering with expressive methods in several examples.
The Markov Pen: Online Synthesis of Free-Hand Drawing Styles
(The Eurographics Association, 2015) Lang, Katrin; Alexa, Marc; David Mould and Pierre Bénard
Learning expressive curve styles from example is crucial for interactive or computer-based narrative illustrations. We propose a method for online synthesis of free-hand drawing styles along arbitrary base paths by means of an autoregressive Markov Model. Choice on further curve progression is made while drawing, by sampling from a series of previously learned feature distributions subject to local curvature. The algorithm requires no useradjustable parameters other than one short example style. It may be used as a custom ''random brush'' designer in any task that requires rapid placement of a large number of detail-rich shapes that are tedious to create manually.

Browse

Browsing NPAR: Non-Photorealistic Animation and Rendering by Title

Results Per Page

Sort Options