P. Haeberli, "Paint by Numbers: Abstract Image Representations," in Proceedings of SIGGRAPH, pp. 207-214, 1990.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....our algorithm with a gallery of images in Section 4. We conclude the paper in Section 5, with a critical appraisal of our technique. 2. Background Research into the field of NPR, specifically the development of painterly renderers, began to gain momentum with Haeberli s interactive paint systems[2]. These permitted a user to rapidly generate impressionist style paintings by creating brush strokes, the colour and orientation of which were determined by point sampling a reference image. This process was labour intensive, and approaches toward automating the production of such paintings were ....

....therefore provides a convenient way of evaluating the relative salience of individual pixels. 3.2 Stroke Generation We now describe the method by which brush strokes are generated, to create a painterly rendering of the original image. We use a novel painting technique adapted from earlier work[2, 8], to generate a series of three dimensional brush strokes; inverted cones with superquadric cross section. The superquadric class of functions can be represented by the equation: a y b = r (2) where a and b are normalised constants (a b = 1) which influence the horizontal ....

[Article contains additional citation context not shown here]

P. Haeberli. Paint by numbers: abstract image representations. In Computer Graphics (Proc. ACM SIGGRAPH), volume 24(4), pages 207--214, 1990.

....techniques are: the type of source data; and the nature of the simulated process. Techniques are classified according to source data into objectspace methods that use the 3D model of a scene to create the rendered image [11, 14] and image space methods that work directly on the 2D image [4, 5]. Hybrid methods take advantage of both 3D and 2D data to produce the final result [9] Most non photorealistic techniques are inspired in traditional visual art forms, such as painting (oil [5] watercolor [1, 18] drawing (pen and ink [7, 2, 22] pencil [19, 21] charcoal [23] and printing ....

.... In object space methods, brush strokes are first associated with the 3D geometry of objects in a scene, and then projected to the image plane defined by a virtual camera [11] In image space methods, brush strokes are placed on the output image, based on 2D information derived from input images [4]. Interactive methods allow the user to guide the rendering process in a manual or semi automatic manner, by indicating where strokes should placed [4] Non interactive methods render the image automatically based on input parameters and data analysis [5] Some methods process a sequence of ....

[Article contains additional citation context not shown here]

Paul E. Haeberli. Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90, 24(4):207--214, August 1990.

.... is perhaps the most thoroughly researched, and a number of methods have been proposed that allow the interactive rendering of surfaces through hatching [6] 7] 8] texturing [9] and stippling [10] Techniques for the interactive illustration of both 3D surfaces [2] 11] 12] and 2D canvas [13], 14] have been developed; other systems allow the virtual engraving and sculpture of more exotic media such as wood [15] Physical simulations of sticky paint [16] watercolour washes and glazes [17] and a variety of artists brushes [14] 18] 19] have been used to create impressive artwork ....

....we are more concerned with the formation of novel images through composition of features. A multitude of methods have more recently been developed to automate the placement of hatches [20] 21] and strokes [22] 23] 24] 25] These contrast with earlier work such as that of Haeberli [13], whose paint systems allowed a user to, for example, interactively generate impressionist style paintings through a labour intensive process. In a similar fashion, sketch rendering systems were initially developed as interactive tools [7] but were later advanced toward greater automation [20] ....

[Article contains additional citation context not shown here]

P. Haeberli, "Paint by numbers: abstract image representations, " in Proceedings Computer Graphics (ACM SIGGRAPH), 1990, vol. 4, pp. 207--214.

....techniques are: the type of source data; and the nature of the simulated process. Techniques are classified according to source data into object space methods that use the 3D model of a scene to create the rendered image [10, 14] and image space methods that work directly on the 2D image [4, 5]. Hybrid methods take advantage of both 3D and 2D data to produce the final result [8] Most non photorealistic techniques are inspired in traditional visual art forms, such as painting (oil [5] watercolor [1, 18] drawing (pen and ink [7, 2, 22] pencil [19, 21] charcoal [23] and printing ....

.... In object space methods, brush strokes are first associated with the 3D geometry of objects in a scene, and then projected to the image plane defined by a virtual camera [10] In image space methods, brush strokes are placed on the output image, based on 2D information derived from input images [4]. Interactive methods allow the user to guide the rendering process in a manual or semi automatic manner, by indicating where strokes should be placed [4] Non interactive methods render the image automatically based on input parameters and data analysis [5] Some methods process a sequence of ....

[Article contains additional citation context not shown here]

Paul E. Haeberli. Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90, 24(4):207--214, August 1990.

....popular approach, e.g. TF97, FTP99, BH00, HJO 01, JEGPO02, KMM 02] However, these work focus on the low level and statistical aspects of styles. Most Non photorealistic techniques offer a control of style through a set of parameters, e.g. Her98] or through direct user interaction, e.g. Hae90, Sch96, KMM 02] Hamel and Strothotte [HS99] capture and re use style using templates that control the parameters of a line renderer. In addition, the subtle variation of style within an image has been shown to be crucial to make the image more lively and focus attention, e.g. WS94, DOM ....

P. Haeberli. Paint by numbers: Abstract image representations. Proce. SIGGRAPH, 1990.

....training images. Pixels are rendered by comparing their neighborhood, and those of a coarser level in a multi resolution pyramid, to neighborhoods of a training image pair. Considering the original image as output and taking its segmentation map as input allows the texture to be painted by numbers [18]. A new image that is composed of the various textures is synthesized by painting a new segmentation map. Swapping the output segmentation map with the original input image results in example based segmentation [8] In our case, we cannot only approximate a common representation for images by ....

P. Haeberli. Paint by numbers: abstract image representations. In ACM Siggraph, pages 207--214, 1990. Impressionist Expressionist Cezanne

....notions into an otherwise purely two dimensional depiction context. This includes texture mapping for cell animation[CJTF98] and shadows for cell animation [PFFL00] or for architectural sketching [TDM01] We finish this overview of attribute systems with a discussion of orientation, e.g. Hae90, SWHS97, ZH00, Hau01] While orientation is used to drive the mark system, it is important to consider it as an attribute, since orientation is a general issue, common to a variety of mark styles. Separating the orientation issue from the particular marks is crucial to build generic modules. Most ....

.... field, e.g. pen and ink strokes [SWHS97] streamlines [TB96] or LIC [CL93] 3D 3D orientation computation have been proposed using iso parametric curves [Elb95] or principal curvatures [ZH00] 3D 2D [ST90] Similarly, 2D exist, e.g. RK00] The 2D 2D category offers both automatic [Hae90, Hau01] and user controlled [Hae90, Ost99, SWHS97] approaches. 6.4 Mark The mark system is the last representational aspect. It deals with the physical medium of the picture. The mark system can be trivial, in particular for realistic graphics where the mark is simply a pixel. On the other end ....

[Article contains additional citation context not shown here]

P. Haeberli. Paint by numbers: Abstract image representations. Proce. SIGGRAPH, 1990.

.... Research in non photorealistic rendering (NPR) has found methods to simulate the effects of various traditional media like pen and ink [4, 27, 28, 34, 35, 19] pencil sketches [1] water color [3] and engraving [21, 30] There has been work on rendering different styles like impressionism [8, 10, 15, 18] and technical illustrations [6, 26, 25] There has also been work on non photorealistic rendering of specific objects like fur and grass [13, 14] To the best of our knowledge, except for an interactive 2D system developed in 1988 [2] we have not seen any work specifically on computer generated ....

Paul E. Haeberli. Paint By Numbers: Abstract Image Representations. In Computer Graphics (SIGGRAPH '90 Proceedings) , volume 24, pages 207--214, August 1990.

....notions into an otherwise purely two dimensional depiction context. This includes texture mapping for cell animation[CJTF98] and shadows for cell animation [PFFL00] or for architectural sketching [TDM01] We finish this overview of attribute systems with a discussion of orientation, e.g. Hae90, SWHS97, ZH00, Hau01] While orientation is used to drive the mark system, it is important to consider it as an attribute, since orientation is a general issue, common to a variety of mark styles. Separating the orientation issue from the particular marks is important to build generic modules. ....

....e.g. pen and ink strokes [SWHS97] streamlines [TB96] or LIC [CL93] 3D # 3D orientation computation have been proposed using iso parametric curves [Elb95] or principal curvatures [ZH00] 3D # 2D [ST90] Similarly, 2. 5D # 2D exist, e.g. RK00] The 2D # 2D category offers both automatic [Hae90, Hau01] and user controlled [Hae90, Ost99, SWHS97] approaches. 5.4 Marks The mark system is the last representational aspect. It deals with the physical medium of the picture. The mark system can be trivial, in particular for realistic graphics where the mark is simply a pixel. On the other end ....

[Article contains additional citation context not shown here]

P. Haeberli. Paint by numbers: Abstract image representations. Proce. SIGGRAPH, 1990.

....as a rendering target and caching mechanism. The system supports multiple display drivers; the simplest one is based on the rview quadtree reconstruction technique. Another driver draws 3D cones that produce a constant interpolation of the Voronoi regions of the sample points in the image plane [4]. Scene geometry is rendered into the back buffer, and the depth buffer is used to identify depth discontinuities in the image. This information is used to constrain the cone drawing along discontinuity edges. The third display representation is a spherical Delaunay mesh [18] which acts as a ....

Paul Haeberli. Paint by numbers: Abstract image representations. In Computer Graphics (Proceedings ACM SIGGRAPH), pages 207--214, 1990.

....a single image, to control the synthesis procedure. One important application of image analogies that we explore in this paper is the automatic synthesis of various artistic styles from examples. In the past few years, there has been a great deal of work in creating artistic styles by computer [10, 21, 24, 26, 32, 36, 41, 42, 50, 51], a field that has come to be known as non photorealistic rendering (NPR) One drawback of most of these previous works, however, is that the methods have had to be specifically tailored to a specific rendering style (or space of styles) image analogies, by contrast, although they may not be able ....

Paul E. Haeberli. Paint By Numbers: Abstract Image Representations. In Computer Graphics (SIGGRAPH '90 Proceedings), volume 24, pages 207--214, August 1990.

....aspects in common with paint systems. Digital paint programs (e.g. 1] are a mainstay of 2D image generation. Multiresolution image painting supports arbitrary resolution images [12, 2] Perlin and Velho [13] provide the ability to paint with multiscale procedural textures. Haeberli and Hanrahan [7] introduced a paint program for painting textures directly onto 3D surfaces (descendents of this algorithms are available in many commerical packages and are commonly used for feature film production) We use similar techniques to interactively define operations on surfaces. 1.2 Outline The ....

Paul E. Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (Proceedings of SIGGRAPH 90), 24(4):207--214, August 1990.

....and Abstract styles. Keywords: Animation, Paint Systems, Temporal Aliasing, Video, Non realistic Rendering 1 Introduction Researchers have developed a variety of tools to modify twodimensional images, giving the results a painterly or handcreated look in such diverse styles as impressionism [7, 8], pen and ink [15] watercolor [2] and engraving [12] Existing NPR rendering methods are essentially filters that take in an image (and possibly some additional processing parameters) and return an altered, NPR version of the original. Because these methods were developed specifically for static ....

....video volume. We will describe each in turn. Figure 4: Impressionist style images from a single preprocess. 3.2.1 Diamonds as 3D Voronoi Cells Many image manipulation programs provide the ability to generate tiled images from input images. The underlying algorithm is based on work by Haeberli [7] in which tiles are actually 2DVoronoi tiles, and the tile colors are sampled from theVoronoi seed point locations. We take the same idea and generalize it to 3D: a video volume can be decomposed into a 3D Voronoi diagram. Then, each slice Figure 5: Results from other impressionist style ....

P. E. Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (Proceedings of SIGGRAPH 90), 24(4):207--214.

....this reason techniques are usually borrowed from artists rather than reinvented from first principles. There has been some prior work applying NPR methods to the depiction of the human form. Haeberli used image processing to produce some stunning images of a woman figure skating in Siggraph 90 [13]. More recently, Cassidy Curtis captured the dynamic quality of human figures using depth buffers to pull out loose and sketchy edge lines. Markosian et al. and Gooch et al. made use of silhouettes to provide cues of depth and shape. In addition Gooch used complementary colors to provide ....

Paul Haeberli. Paint By Numbers: Abstract Image Representation. In SIGGRAPH 90 Conference Proceedings, August 1990.

.... Research in non photorealistic rendering (NPR) has found methods to help artists generate imagery in various traditional media like pen and ink [4, 25, 26, 28, 29, 17] pencil sketches [1] water color [3] and engraving [19, 27] There has been work on rendering different styles like impressionism [8, 10, 14, 16], rendering of fur and grass [12, 13] and technical illustrations [6, 24, 23] However, to the best of our knowledge, except for an interactive 2D system developed in 1988 [2] we have not seen any work on computer generated 3D charcoal rendering. In this paper, we present a rendering algorithm ....

Paul E. Haeberli. Paint By Numbers: Abstract Image Representations. In Computer Graphics (SIGGRAPH '90 Proceedings), volume 24, pages 207--214, August 1990.

....the early history of computer graphics, visual style was dominated by either performance limitations or attempts to achieve photorealism. A movement within the community to display images in non photorealistic, artistic styles began to gain momentum with Haeberli s impressionist painting programs [6] and Saito and Takahashi s Comprehensible Renderering paper [16] These were soon followed by commercial tools such as Fractal Painter [3] Since then, there has been an explosion of new styles presented at SIGGRAPH and other venues. Just a few examples include impressionist painting [12] ....

Paul E. Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (Proceedings of SIGGRAPH 90), 24(4).

.... and ink is proposed in [24] Interactive creating pen andink line style drawings from gray scale images is introduced in [21] Various artistic effects of watercolor and their automatic simulation are described in [4] Line art drawing is studied in [5 8,11,19] Expressive rendering is proposed in [10,12]. In [14] digital facial engraving, which imitates traditional copperplate engraving starting from a digital photo of a person, is introduced. In [3,17] methods of carving and sculpting based on 2D images, where the color of each point defines how high or deep the elevation of the respective 3D ....

Haeberli P (1990) Paint by Numbers: Abstract Image Representation. Comput Graph 24:207-214.

.... direction fields into a real time hatching system for shading 3D models of arbitrary topology (6) 2 Previous work Much of the work in non photorealistic rendering has focused on tools to help artists (or non artists) generate imagery in various traditional media or styles such as impressionism [5, 12, 14], technical illustration [4, 19, 20] pen and ink [1, 21, 22, 26, 27] and engraving [16] Our work is applicable over a range of styles in which individual strokes are visible. One way to categorize NPR methods would be to consider the form of input used. One branch of stroke based NPR work uses ....

....22, 26, 27] and engraving [16] Our work is applicable over a range of styles in which individual strokes are visible. One way to categorize NPR methods would be to consider the form of input used. One branch of stroke based NPR work uses a reference image for color, tone, or orientation, e.g. [5, 21, 22]. For painterly processing of video, Litwinowitcz [12] and later Hertzmann and Perlin [6] addressed the challenge of frame toframe coherence by applying optical flow methods to approximate object space coherence for strokes. Our work follows a branch of research that relies on 3D models for ....

HAEBERLI, P. E. Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90, 207--214.

No context found.

P. Haeberli, "Paint by Numbers: Abstract Image Representations," in Proceedings of SIGGRAPH, pp. 207-214, 1990.

No context found.

HAEBERLI, P. E. 1990. Paint by numbers: Abstract image representations. In Proceedings of SIGGRAPH 90, 207--214.

No context found.

, Haeberli, Paul, "Paint by Numbers: Abstract Image Representations," Computer Graphics, 24(4), August 1990.

No context found.

P. Haeberli. Paint by numbers: Abstract image representations. In Proceedings of ACM SIGGRAPH 90, pages 207--214, 1990.

No context found.

P. Haeberli. Paint by numbers: Abstract image representation. SIGGRAPH Conf. Proc., pages 573--580, 1990.

No context found.

P. Haeberli. Paint By Numbers: Abstract Image Representations. In Proceedings of ACM SIGGRAPH 90, pages 207--214, August 1990.

No context found.

P. Haeberli, "Paint by Numbers: Abstract Image Representations," in Proceedings of SIGGRAPH, pp. 207-214, 1990.

No context found.

Haeberli, P.: Paint by Numbers: Abstract Image Representation, Siggraph, Computer Graphics vol. 24, number 4, 1990

No context found.

Paul E. Haeberli. Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90, 24(4):207--214, August 1990.

No context found.

P.E. Haeberli, "Paint by numbers: Abstract image representations", Computer Graphics, (Proc. SIGGRAPH' 1990.

No context found.

Haeberli, P. 1990. Paint by numbers: Abstract image representations. In Proc. of ACM SIGGRAPH 90, 207--214.

No context found.

HAEBERLI P.: Paint By Numbers: Abstract Image Representations. In Proceedings of ACM SIGGRAPH 90 (August 1990), pp. 207--214.

No context found.

P. Haeberli. Paint by numbers: Abstract image representations. In Proc. of SIGGRAPH'90, pages 207--214, 1990.

No context found.

P. Haeberli. Paint by numbers: abstract image representations. In Proceedings Computer Graphics (ACM SIGGRAPH), volume 4, pages 207--214, 1990.

No context found.

Haeberli, P.: Paint by Numbers: Abstract Image Representation, Siggraph, Computer Graphics vol. 24, number 4, 1990

No context found.

Paul Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (SIGGRAPH 90 Conference Proceedings), 24(4):207--214, 1990.

No context found.

P. E. Haeberli, Paint by numbers: Abstract image representations. In Computer Graphics (SIGGRAPH 90 Proceedings), F. Baskett, ed., vol. 24, Aug. 1990, 207--214.

No context found.

Paul E. Haeberli. Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90, 24(4):207--214, August 1990.

No context found.

Haeberli, P.: Paint by numbers: Abstract image representations. Proce. SIGGRAPH (1990)

No context found.

Haeberli, P.: Paint By Numbers: Abstract Image Representation. In: SIGGRAPH 90 Conference Proceedings. (1990)

No context found.

P. E. Haeberli. Paint by numbers: Abstract image representations. In Proceedings of SIGGRAPH 90, pages 207--214, 1990.

No context found.

P. E. Haeberli. Paint by numbers: Abstract image representations. In SIGGRAPH 90 Conference Proceedings, pages 207--214. ACM SIGGRAPH, Addison Wesley, 1990.

No context found.

P. E. Haeberli. Paint by numbers: Abstract image representations. In F. Baskett, editor, Computer Graphics (SIGGRAPH '90 Proceedings), volume 24, pages 207--214, Aug. 1990. 18

No context found.

Paul E. Haeberli. Paint by numbers: Abstract image representations. In Forest Baskett, editor, Computer Graphics (SIGGRAPH '90 Proceedings), volume 24, pages 207--214, August 1990.

No context found.

HAEBERLI,P.E.Paint by numbers: Abstract image representations. Proceedings of SIGGRAPH 90 24,4(August 1990), 207--214.

No context found.

P. Haeberli. Paint by numbers: Abstract image representations. In Proceedings of the 17th annual conference on Computer graphics and interactive techniques, pages 207--214. ACM Press, 1990.

No context found.

P. E. Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (Proceedings of SIGGRAPH 90), 24:207--214, 1990.

No context found.

P. Haeberli, "Paint by numbers: abstract image representations," in Proceedings Computer Graphics (ACM SIGGRAPH), 1990, vol. 4, pp. 207--214.

No context found.

P. E. Haeberli, Paint by numbers: Abstract image representations, Computer Graphics 24 (4) (1990) 207--214.

No context found.

Paul E. Haeberli. Paint by numbers: Abstract image representations. Computer Graphics (Proceedings of SIGGRAPH 90), 24(4):207--214, August 1990. ISBN 0-201-50933-4. Held in Dallas, Texas.

No context found.

P.E. Haeberli, "Paint by numbers: Abstract image representations", Computer Graphics, (Proc. SIGGRAPH'

No context found.

Hae90. P. Haeberli. Paint by numbers: Abstract image representations. In SIGGRAPH, 1990.

First 50 documents  Next 50

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC