Ran Gal, O. Sorkine-Hornung, T. Popa, A. Sheffer, D. Cohen-Or
The ability of computer graphics to represent images symbolically has so far been used mostly to render existing models with greater clarity or with greater visual appeal. In this work, we present a method aimed at harnessing this symbolic representation power to increase the expressiveness of the 3D models themselves. We achieve this through modification of the actual representation of 3D shapes rather than their images. In particular, we focus on 3D collage creation, namely, a generation of compound representations of objects. The ability of such representations to convey multiple meanings has been recognized for centuries. At the same time, it has also been acknowledged that for humans, the creation of compound 3D shapes is extremely taxing. Thus, this expressive but technically challenging artistic medium is a particularly good candidate to address using computer graphics methods. We present an algorithm for 3D collage generation that serves as an artistic tool performing the challenging 3D processing tasks, thus enabling the artist to focus on the creative side of the process.
{"title":"3D collage: expressive non-realistic modeling","authors":"Ran Gal, O. Sorkine-Hornung, T. Popa, A. Sheffer, D. Cohen-Or","doi":"10.1145/1274871.1274873","DOIUrl":"https://doi.org/10.1145/1274871.1274873","url":null,"abstract":"The ability of computer graphics to represent images symbolically has so far been used mostly to render existing models with greater clarity or with greater visual appeal. In this work, we present a method aimed at harnessing this symbolic representation power to increase the expressiveness of the 3D models themselves. We achieve this through modification of the actual representation of 3D shapes rather than their images. In particular, we focus on 3D collage creation, namely, a generation of compound representations of objects. The ability of such representations to convey multiple meanings has been recognized for centuries. At the same time, it has also been acknowledged that for humans, the creation of compound 3D shapes is extremely taxing. Thus, this expressive but technically challenging artistic medium is a particularly good candidate to address using computer graphics methods. We present an algorithm for 3D collage generation that serves as an artistic tool performing the challenging 3D processing tasks, thus enabling the artist to focus on the creative side of the process.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130999410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Christopher DeCoro, Forrester Cole, Adam Finkelstein, S. Rusinkiewicz
While much research has focused on rendering physically-correct shadows, a "correct" shadow often exhibits unnecessary detail that distracts from the primary subject of the scene. Artists often prefer to have creative control over the rendered appearance of the shadow. This paper presents an algorithm offering control over stylized shadows, based on four intuitive parameters - inflation, brightness, softness, and abstraction - that together support a broad range of effects. The algorithm, which works largely in image space, can easily be incorporated into existing rendering pipelines, and is independent of scene geometry or shadow determination method.
{"title":"Stylized shadows","authors":"Christopher DeCoro, Forrester Cole, Adam Finkelstein, S. Rusinkiewicz","doi":"10.1145/1274871.1274884","DOIUrl":"https://doi.org/10.1145/1274871.1274884","url":null,"abstract":"While much research has focused on rendering physically-correct shadows, a \"correct\" shadow often exhibits unnecessary detail that distracts from the primary subject of the scene. Artists often prefer to have creative control over the rendered appearance of the shadow. This paper presents an algorithm offering control over stylized shadows, based on four intuitive parameters - inflation, brightness, softness, and abstraction - that together support a broad range of effects. The algorithm, which works largely in image space, can easily be incorporated into existing rendering pipelines, and is independent of scene geometry or shadow determination method.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126057100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents a non-photorealistic rendering technique that automatically generates a line drawing from a photograph. We aim at extracting a set of coherent, smooth, and stylistic lines that effectively capture and convey important shapes in the image. We first develop a novel method for constructing a smooth direction field that preserves the flow of the salient image features. We then introduce the notion of flow-guided anisotropic filtering for detecting highly coherent lines while suppressing noise. Our method is simple and easy to implement. A variety of experimental results are presented to show the effectiveness of our method in producing self-contained, high-quality line illustrations.
{"title":"Coherent line drawing","authors":"Henry Kang, Seungyong Lee, C. Chui","doi":"10.1145/1274871.1274878","DOIUrl":"https://doi.org/10.1145/1274871.1274878","url":null,"abstract":"This paper presents a non-photorealistic rendering technique that automatically generates a line drawing from a photograph. We aim at extracting a set of coherent, smooth, and stylistic lines that effectively capture and convey important shapes in the image. We first develop a novel method for constructing a smooth direction field that preserves the flow of the salient image features. We then introduce the notion of flow-guided anisotropic filtering for detecting highly coherent lines while suppressing noise. Our method is simple and easy to implement. A variety of experimental results are presented to show the effectiveness of our method in producing self-contained, high-quality line illustrations.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131406892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pictures taken from different view points cannot be stitched into a geometrically consistent mosaic, unless the structure of the scene is very special. However, geometrical consistency is not the only criterion for success: incorporating multiple view points into the same picture may produce compelling and informative representations. A multi viewpoint form of visual expression that has recently become highly popular is that of joiners (a term coined by artist David Hockney). Joiners are compositions where photographs are layered on a 2D canvas, with some photographs occluding others and boundaries fully visible. Composing joiners is currently a tedious manual process, especially when a great number of photographs is involved. We are thus interested in automating their construction. Our approach is based on optimizing a cost function encouraging image-to-image consistency which is measured on point-features and along picture boundaries. The optimization looks for consistency in the 2D composition rather than 3D geometrical scene consistency and explicitly considers occlusion between pictures. We illustrate our ideas with a number of experiments on collections of images of objects, people, and outdoor scenes.
{"title":"Automating joiners","authors":"Lihi Zelnik-Manor, P. Perona","doi":"10.1145/1274871.1274890","DOIUrl":"https://doi.org/10.1145/1274871.1274890","url":null,"abstract":"Pictures taken from different view points cannot be stitched into a geometrically consistent mosaic, unless the structure of the scene is very special. However, geometrical consistency is not the only criterion for success: incorporating multiple view points into the same picture may produce compelling and informative representations. A multi viewpoint form of visual expression that has recently become highly popular is that of joiners (a term coined by artist David Hockney). Joiners are compositions where photographs are layered on a 2D canvas, with some photographs occluding others and boundaries fully visible.\u0000 Composing joiners is currently a tedious manual process, especially when a great number of photographs is involved. We are thus interested in automating their construction. Our approach is based on optimizing a cost function encouraging image-to-image consistency which is measured on point-features and along picture boundaries. The optimization looks for consistency in the 2D composition rather than 3D geometrical scene consistency and explicitly considers occlusion between pictures. We illustrate our ideas with a number of experiments on collections of images of objects, people, and outdoor scenes.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130964109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Alexandrina Orzan, A. Bousseau, Pascal Barla, J. Thollot
Visual content is often better communicated by simplified or exaggerated images than by the "real world like" images. In this paper, we offer a tool for creating such enhanced representations of photographs in a way consistent with the original image content. To do so, we develop a method to identify the relevant image structures and their importance. Our approach (a) uses edges as the basic structural unit in the image, (b) proposes tools to manipulate this structure in a flexible way, and (c) employs gradient domain image processing techniques to reconstruct the final image from a "cropped" gradient information. This edge-based approach to non-photorealistic image processing is made feasible by two new techniques we introduce: an addition to the Gaussian scale space theory to compute a perceptually meaningful hierarchy of structures, and a contrast estimation method necessary for faithful gradient-based reconstructions. We finally present various applications that manipulate image structure in different ways.
{"title":"Structure-preserving manipulation of photographs","authors":"Alexandrina Orzan, A. Bousseau, Pascal Barla, J. Thollot","doi":"10.1145/1274871.1274888","DOIUrl":"https://doi.org/10.1145/1274871.1274888","url":null,"abstract":"Visual content is often better communicated by simplified or exaggerated images than by the \"real world like\" images. In this paper, we offer a tool for creating such enhanced representations of photographs in a way consistent with the original image content. To do so, we develop a method to identify the relevant image structures and their importance. Our approach (a) uses edges as the basic structural unit in the image, (b) proposes tools to manipulate this structure in a flexible way, and (c) employs gradient domain image processing techniques to reconstruct the final image from a \"cropped\" gradient information. This edge-based approach to non-photorealistic image processing is made feasible by two new techniques we introduce: an addition to the Gaussian scale space theory to compute a perceptually meaningful hierarchy of structures, and a contrast estimation method necessary for faithful gradient-based reconstructions. We finally present various applications that manipulate image structure in different ways.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124537865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Winnemöller, David Feng, B. Gooch, Satoru Suzuki
We present a psychophysical experiment to determine the effectiveness of perceptual shape cues for rigidly moving objects in an interactive, highly dynamic task. We use standard non-photorealistic (NPR) techniques to carefully separate and study shape cues common to many rendering systems. Our experiment is simple to implement, engaging and intuitive for participants, and sensitive enough to detect significant differences between individual shape cues. We demonstrate our experimental design with a user study. In that study, participants are shown 16 moving objects, 4 of which are designated targets, rendered in different shape-from-X styles. Participants select targets projected onto a touch-sensitive table. We find that simple Lambertian shading offers the best shape cue in our user study, followed by contours and, lastly, texturing. Further results indicate that multiple shape cues should be used with care, as these may not behave additively.
{"title":"Using NPR to evaluate perceptual shape cues in dynamic environments","authors":"H. Winnemöller, David Feng, B. Gooch, Satoru Suzuki","doi":"10.1145/1274871.1274885","DOIUrl":"https://doi.org/10.1145/1274871.1274885","url":null,"abstract":"We present a psychophysical experiment to determine the effectiveness of perceptual shape cues for rigidly moving objects in an interactive, highly dynamic task. We use standard non-photorealistic (NPR) techniques to carefully separate and study shape cues common to many rendering systems. Our experiment is simple to implement, engaging and intuitive for participants, and sensitive enough to detect significant differences between individual shape cues. We demonstrate our experimental design with a user study. In that study, participants are shown 16 moving objects, 4 of which are designated targets, rendered in different shape-from-X styles. Participants select targets projected onto a touch-sensitive table. We find that simple Lambertian shading offers the best shape cue in our user study, followed by contours and, lastly, texturing. Further results indicate that multiple shape cues should be used with care, as these may not behave additively.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129070926","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Research in human visual cognition suggests that beautiful images can engage the visual system, encouraging it to linger in certain locations in an image and absorb subtle details. By developing aesthetically pleasing visualizations of data, we aim to engage viewers and promote prolonged inspection, which can lead to new discoveries within the data. We present three new visualization techniques that apply painterly rendering styles to vary interpretational complexity (IC), indication and detail (ID), and visual complexity (VC), image properties that are important to aesthetics. Knowledge of human visual perception and psychophysical models of aesthetics provide the theoretical basis for our designs. Computational geometry and nonphotorealistic algorithms are used to preprocess the data and render the visualizations. We demonstrate the techniques with visualizations of real weather and supernova data.
{"title":"Engaging viewers through nonphotorealistic visualizations","authors":"Laura G. Tateosian, C. Healey, J. Enns","doi":"10.1145/1274871.1274886","DOIUrl":"https://doi.org/10.1145/1274871.1274886","url":null,"abstract":"Research in human visual cognition suggests that beautiful images can engage the visual system, encouraging it to linger in certain locations in an image and absorb subtle details. By developing aesthetically pleasing visualizations of data, we aim to engage viewers and promote prolonged inspection, which can lead to new discoveries within the data. We present three new visualization techniques that apply painterly rendering styles to vary interpretational complexity (IC), indication and detail (ID), and visual complexity (VC), image properties that are important to aesthetics. Knowledge of human visual perception and psychophysical models of aesthetics provide the theoretical basis for our designs. Computational geometry and nonphotorealistic algorithms are used to preprocess the data and render the visualizations. We demonstrate the techniques with visualizations of real weather and supernova data.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129446244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we present a hybrid algorithm for determining the quantitative invisibility (QI) of scene edges. This is accomplished by drawing the edges and faces of each model using hardware blending to create an ID image. Then a simple counting problem yields the QI of each edge. This method automatically determines which edges must be split due to silhouette occlusion and surface intersection, making this algorithm faster than previous hybrid visibility algorithms for complex scenes. We demonstrate the utility of hybrid QI by presenting a method for removing silhouette degeneracies based on the QI of sihouette edges.
{"title":"Hybrid quantitative invisibility","authors":"Matthew Kaplan","doi":"10.1145/1274871.1274879","DOIUrl":"https://doi.org/10.1145/1274871.1274879","url":null,"abstract":"In this paper, we present a hybrid algorithm for determining the quantitative invisibility (QI) of scene edges. This is accomplished by drawing the edges and faces of each model using hardware blending to create an ID image. Then a simple counting problem yields the QI of each edge. This method automatically determines which edges must be split due to silhouette occlusion and surface intersection, making this algorithm faster than previous hybrid visibility algorithms for complex scenes. We demonstrate the utility of hybrid QI by presenting a method for removing silhouette degeneracies based on the QI of sihouette edges.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114601368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Martin Schwarz, Tobias Isenberg, Katherine Mason, Sheelagh Carpendale
Non-photorealistic rendering has placed much emphasis on developing algorithms that determine the appearance of renditions. To successfully deploy NPR rendering systems using these algorithms, however, one has to consider how artists, illustrators, or lay people can influence the created renditions. Many systems require a cyclical process of parameter tweaking, rendering, and validation before one is satisfied with the final rendition. We present an interactive NPR canvas in which a user can construct a rendition with pre-rendered primitives and modify these primitives using tools that provide spatially explicit computational assistance. We call this approach modeling with rendering primitives. Our technique has the advantage of algorithmic support for creating NPR renditions but requires neither global parameter adjustments and re-rendering cycles nor attribute changes on individually selected primitives. We demonstrate the applicability of this interaction technique for the creation of painterly rendering, pointillism, and decorative mosaics.
{"title":"Modeling with rendering primitives: an interactive non-photorealistic canvas","authors":"Martin Schwarz, Tobias Isenberg, Katherine Mason, Sheelagh Carpendale","doi":"10.1145/1274871.1274874","DOIUrl":"https://doi.org/10.1145/1274871.1274874","url":null,"abstract":"Non-photorealistic rendering has placed much emphasis on developing algorithms that determine the appearance of renditions. To successfully deploy NPR rendering systems using these algorithms, however, one has to consider how artists, illustrators, or lay people can influence the created renditions. Many systems require a cyclical process of parameter tweaking, rendering, and validation before one is satisfied with the final rendition. We present an interactive NPR canvas in which a user can construct a rendition with pre-rendered primitives and modify these primitives using tools that provide spatially explicit computational assistance. We call this approach modeling with rendering primitives. Our technique has the advantage of algorithmic support for creating NPR renditions but requires neither global parameter adjustments and re-rendering cycles nor attribute changes on individually selected primitives. We demonstrate the applicability of this interaction technique for the creation of painterly rendering, pointillism, and decorative mosaics.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"7 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114843499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ryan M. Schmidt, Tobias Isenberg, P. Jepp, Karan Singh, B. Wyvill
Inspired by the comic-book production pipeline, a method is proposed for integrating visual aspects of the sketching process into 3D sketch-based modeling systems. In particular, artist-drawn construction aids called visual scaffolding are explored. Two scaffolding components which simulate elements of pencil sketching, geometric massing and eraser marks, are integrated into a rendering pipeline which also includes a suite of new object-space techniques for high-fidelity pen-and-ink depiction of implicit surfaces. Based on a hybrid, hierarchical approach which leverages both the implicit surface definition and an underlying coarse tessellation, new methods are described for computing silhouettes, suggestive contours, surface stippling, and surfel-based visibility culling. These techniques are real-time but require no pre-computation, allowing them to be applied to dynamic hierarchical implicit surfaces, and are demonstrated in ShapeShop, an interactive sketch-based modeling tool. The result is a real-time display pipeline which composites these novel scaffolding and pen-and-ink techniques to depict a visual history of the modeling process.
{"title":"Sketching, scaffolding, and inking: a visual history for interactive 3D modeling","authors":"Ryan M. Schmidt, Tobias Isenberg, P. Jepp, Karan Singh, B. Wyvill","doi":"10.1145/1274871.1274875","DOIUrl":"https://doi.org/10.1145/1274871.1274875","url":null,"abstract":"Inspired by the comic-book production pipeline, a method is proposed for integrating visual aspects of the sketching process into 3D sketch-based modeling systems. In particular, artist-drawn construction aids called visual scaffolding are explored. Two scaffolding components which simulate elements of pencil sketching, geometric massing and eraser marks, are integrated into a rendering pipeline which also includes a suite of new object-space techniques for high-fidelity pen-and-ink depiction of implicit surfaces. Based on a hybrid, hierarchical approach which leverages both the implicit surface definition and an underlying coarse tessellation, new methods are described for computing silhouettes, suggestive contours, surface stippling, and surfel-based visibility culling. These techniques are real-time but require no pre-computation, allowing them to be applied to dynamic hierarchical implicit surfaces, and are demonstrated in ShapeShop, an interactive sketch-based modeling tool. The result is a real-time display pipeline which composites these novel scaffolding and pen-and-ink techniques to depict a visual history of the modeling process.","PeriodicalId":204343,"journal":{"name":"International Symposium on Non-Photorealistic Animation and Rendering","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122068120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：