Image-Space Painterly Rendering

Size: px
Start display at page:

Download "Image-Space Painterly Rendering"

Transcription

1 Image-Space Painterly Rendering Janne Hellstén Helsinki University of Technology Abstract In this paper two painterly rendering techniques are described. Both techniques automatically transform images into painted-like images using impressionistic image filters. Litwinowicz concentrates in his work on video sequences and achieves frame-to-frame coherence by the use of optical flow in a novel way. Hertzmann presents an excellent image filter that creates images with a handpainted appearance using a multi-resolution brush stroke rendering method. 1 INTRODUCTION For years, computer graphics research has focused on creating images and animations that are photorealistic. However, photorealistic image synthesis is not in all applications required or even wanted. In some cases, an image that accentuates a certain look or feel can be more desirable than a photorealistic image. An image that depicts a subject too accurately can also be misleading and constraining, a good example of fighting this problem is Teddy Painter (Igarashi et al., 1999) Teddy Painter hides the technical side of modeling by using illustrated rendering (Markosian et al., 1997; Salisbury et al., 1997), achieving great results. Apart from pen-and-ink illustrated rendering there exist painterly rendering techniques, which aim for creating images having qualities unique to the art of painting. These techniques differ from pen-and-ink rendering in that shapes are distinguished by variations of color rather than by outline or contour. Most of the painterly rendering styles are inspired by the late 1800 s impressionistic artists, for example Claude Monet and Vincent van Gogh. These painters strove to capture their subjective impressions of the world on canvas instead of photographing precise images. 1.1 Related work In Haeberli s early work, he presents a painting program for creating impressionistic images (Haeberli, 1990). Although the presented technique produces striking results, the process of image creation requires vast amounts of user interaction. 1

2 In 1996, Meier proposed a brush rendering technique (Meier, 1996). The paper addresses the difficult problem of frame-to-frame coherence when displaying painterly rendered animation. However, the used technique is based on 3D-information and cannot as such be applied to 2D-images or 2D-image sequences. Brush stroke techniques are also used in Treavett s work. Although their brush model is rather primitive, they deserve credit for their statistical treatment of stroke placement (Treavett & M. Chen, 1997). Painterly rendering and non-photorealistic rendering techniques have been in use in commercial imaging software. Most of the techniques used, however, are usually very simple but such simple algorithms can be very effective when used with care. Adobe Systems has used many standard image processing filters to with great success in their Photoshop (Adobe Systems, 1996). 1.2 Overview To simulate a human painter, one must somehow simulate the process of painting a picture by hand. The one most important thing in the process of painting a painting is how an artist transforms his subjective picture or an impression of the world into the canvas. This transform usually involves the use of a brush and colors as the main tool. This process is strongly analogous to the way painterly rendering algorithms work the algorithm sees a parametrization of the world (usually a digital image) and must somehow transform the parametrization into a new parametrization having desired attributes. So the most obvious place to start is to simulate the use of colors and a brush digitally. The process of drawing an image using brush strokes is usually divided into separate tasks: the selection of brush strokes color, texture and shape; the rendering of the prepared strokes; and finally, in the case of animation, animating the brush strokes and creating new ones as needed. Some authors have even gone so far as to simulate the actual physics of a brush stroke (Strassman, 1986; Curtis et al., 1997), but the direction most researches have chosen is to approximate a stroke by some ad hoc method that produces satisfactory results. This is the way both Litwinowicz and Hertzmann have chosen. These two authors both present techniques for automatical brush stroke placement and stroke rendering. Litwinowicz also presents a novel way to handle brush stroke animation when rendering painterly animation out of ordinary videos. Neither of the techniques require any user interaction during the rendering process. In the next two sections we proceed to more detailed descriptions of the two techniques reviewed. And finally in section 4 we wrap up the subject and discuss possible future research directions. 2

3 Figure 1: Edge clipping. Note how the brush stroke gets clipped at the edges of the shape. 2 LITWINOWICZ In this section we describe the algorithm presented by Litwinowicz in more detail (Litwinowicz, 1997). The primary focus of the aforementioned paper is how to deal with temporal continuity when rendering painterly animation. 2.1 Rendering of brush strokes We start by defining a brush stroke. A brush stroke is a line having a radius of R, location in the image of (C x,c y ) and a direction of A. Suppose we now had a thousand of these brush stroke definitions, each stroke having additional one more attribute: stroke color (color). We could proceed straight to rendering the final image with a simple algorithm outlined below. for each stroke drawedgeclippedline((c x,c y ),A of width R with color color) Now, if all the parameters were set properly, we would have a nice painterly rendered image. What follows, is a description of an algorithm that given an input image creates all the necessary parameters for rendering the output image with the aforementioned algorithm. We assign a brush stroke for each two pixels in both X and Y directions in the source image, although this density can be a user-supplied parameter. The distribution of strokes must be dense enough to assure that strokes, when rendered, fully cover the output image. In order to render the actual strokes into the final image, a custom line drawing routine is needed in order to preserve edges in the source image. The line drawing routine has to first determine the endpoints of the stroke and then render the stroke. The endpoints are determined by an algorithm that starts from the center of the brush 3

4 stroke((c x,c y )) and traverses the source image in the direction of the stroke until an edge is found. 1 or a maximum line length is exceeded. See figure 1 for a depiction of the line-edge clipping process. To have the brush strokes follow the contours and shapes of the input image, a method for aligning each stroke to closely match the input image s local detail is needed. This alignment is carried out by finding a direction (angle A) for each stroke based on the local image gradient. Having the strokes oriented in the direction normal to the image gradient makes the strokes align to directions where there are relatively small changes in image intensity. The image gradient values are calculated from the Gaussian filtered source image. The blurring of the source image is performed to accommodate for noise in the source images, especially in the case of video sequences. This works well for some cases, but when the source image has large areas of constant or near constant color, the magnitude of image gradient approaches zero and causes distracting visual artifacts. This can be accommodated for by using a more sophisticated image gradient calculation method that uses neighbouring good image gradient values in areas of constant color. 2.2 Using optical flow to achieve frame-to-frame coherence When rendering painterly rendered animations, care must be taken to maintain frameto-frame coherence. In most non-photorealistic rendering systems, a subtle change in the input image can cause dramatic changes in the output image. This fact complicates the process of creating painterly animations out of video sequences; two sequential frames can differ too much when run through a painterly filter. This causes distracting artifacts when rendering painterly animations the animation does not seem smooth and continuous anymore when frames are changing incoherently. In Litwinowicz s work things are not any bit different. If the brush stroke rendering part of the paper would be applied for animation, the resulting animation would no doubt be scintillating. However, Litwinowicz suggests the use of optical flow to aid the animation process. Two dimensional optical flow vectors are typically used in machine vision systems (Sonka et al., 1993). These vectors describe the motion of each of portion of the image in the image plane. Optical flow can be directly applied to brush strokes. Instead of rendering each frame from scratch, calculated brush strokes are stored in memory and moved according to the optical flow. For each frame, some new brush strokes are introduced and some old ones are removed. The painterly animation rendering process begins with the calculation of the optical flow from the video sequence. The first frame of the output sequence is painted normally, as described in the previous section. As we proceed to painting the next frame we use the brush strokes calculated in the previous frame and move them in the direction of the optical flow. This will cause the strokes to sort of stick to the objects 1 A Sobel filtered Gaussian blurred version of the source image is used to detect the edges. 4

5 and shapes in the animation. However, as the the painting process continues, eventually some of the strokes will drift out of the image and some areas the image will be over-populated with strokes. To have the density of strokes remain constant over the image plane, new brush strokes need to be introduced and some old strokes need to be removed. An algorithm is needed for determining which areas are over-populated and which areas are underpopulated. In order to measure the brush stroke population over the image plane, a Delaunay triangulation is built based on the brush stroke center locations. Delaunay triangulation will cover the whole input image with triangles. The triangulation is then subdivided until a maximum area constraint is satisfied, that is, the mesh does not contain any triangles having a larger area than a predetermined maximum area. The new vertices resulting from this subdivision process are then used as new brush stroke center points. The removal of brush strokes from overly dense areas is also done through the use of the Delaunay triangulation. The edge list of the previously calculated triangulation is traversed and all brush strokes not satisfying a supplied minimum edge length constraint are discarded. The test is done by finding the length of each neighboring edge and testing that length against the predetermined minimum edge length. When the current brush stroke set is updated, the rendering of brush strokes will follow as described in the previous section. New colors and new orientations will be calculated for the strokes and the strokes will again be rendered in random order, with the exception of new strokes which are rendered after the old strokes from the previous frames to prevent popping artifacts. 3 HERTZMANN In this section a painterly rendering technique by Hertzmann is described (Hertzmann, 1998). Instead of using brush strokes of same size and shape like Litwinowicz did, Hertzmann uses brush strokes that are modeled using spline curves of varying thickness. The rendering is divided into multiple passes instead of rendering the whole picture in one go. This technique nicely captures small and large detail in the source image and is similar to some painting techniques where a painter first paints the image composition in coarse detail and then adding more brush strokes to areas needing more detail. In a sense, this progressive rendering technique is similar to Laplacian pyramid image-encoding (Burt & Adelson, 1983) Progressive rendering The image is rendered in multiple passes each pass having a different brush size. The first pass is rendered with the largest brush size and for each pass, the brush size is 2 To reconstruct an image out of a Laplacian pyramid, one first starts with the lowest, coarsest, level of the pyramid and then incrementally adds more high-frequency data. 5

6 progressively made smaller to capture more high-frequency detail. First the output image, canvas, is initialized to a constant color. For each pass, a reference image is constructed out of the source image by filtering with a Gaussian kernel of width w i. 3 Filtering is done to throw out detail that couldn t be captured with the current brush size. The current reference image is given as input to a sub-routine (named paintlayer, see pseudocode below) that will paint brush strokes of width R i on the canvas. This routine first determines the areas in the picture where more brushes need to be drawn. This is done by comparing the difference between the canvas and the input image. If a certain area s difference exceeds a predefined threshold T, a brush stroke will be added into that area. The brush stroke is placed in the location of largest error between the canvas and the reference image. This is to avoid missing small details in the input image and also to prevent visual regularities from appearing in the painted image. paintlayer(canvas, ref, src, R i ) { for x = 0 to imagewidth, x+=grid for y = 0 to imageheight, y+=grid { E,(x b,y b ) = meanerror(canvas,ref,x,y,grid) if E > T then { addbrushstroke(r i,(x b,y b ),ref,src) } } render brush strokes } In the above pseudocode, the whole image is traversed and brush strokes are added as needed. The function meanerror() returns the mean-square error between two source image in a given region. It also returns a location in the input region having the largest deviation from the canvas to the source image. The function addbrush- Stroke() is called for regions in the canvas that differ too much from the reference image. This function will do the actual rendering of the stroke, as described in the next section. 3.2 Brush stroke spline generation We will now continue to the details of rendering the actual brush strokes. Each brush stroke is a spline consisting of N control points. In order to render a stroke, an algorithm for determining the locations of the control points is needed. 3 The filter width w i is set equal or relative to the brush width R i. 6

7 Figure 2: Brush stroke generation. Control points for the brush stroke s spline are generated by walking along a path in the Sobel filtered reference image in the direction normal to the image gradient. On the left is the reference image and on the right is a filtered reference image showing the magnitude of the image gradient for each pixel. The algorithm first starts at a point (x 0,y 0 ) and picks a color for the stroke at that location from the source image. This point is the first control point in the spline. At (x 0,y 0 ), the Sobel filtered luminance of the reference image 4 is sampled and used to calculate the next control point (x 1,y 1 ) by moving R i pixels in the sampled direction. At each new location (x j,y j ) the same procedure is executed. This process is continued until either a maximum predetermined length of a stroke is reached or the difference between stroke color deviates too much from the current color at (x j,y j ). See figure 2 for a depiction of a brush stroke generation note how the stroke follows an edge in the reference image. When the control points are calculated, the brush stroke is rendered by rendering filled circles of radius R i along the spline. All the strokes are drawn in random order to minimize regularities in the output image. The random order can be achieved without storing the brush stroke splines by making the paintlayer-routine of the previous section to traverse the image in random order or by using a random Z-buffer as suggested in Hertzmann s paper. 3.3 Style parameters For an artist to use a painterly algorithm, the algorithm needs to be able to create output images of different styles there is no one style that would be the right choice for everything. Therefore the painterly algorithm must be ready to produce different styles based on user defined parameters. Consider a real painter. What are the charasteristics of his brush usage when he 4 See section 2.1 for discussion on using image gradients to guide brush strokes 7

8 Figure 3: Different styles. The image on the left uses smaller brush strokes while the image on the right uses bigger strokes making it more coarse. wants to paint in a certain style? The selection of a brush is one the painter might choose a larger brush for coarser regions in the painting. The painter must also choose the right medium whether he chooses oil or watercolor depends on his subjective preferences and the work at hand. Much of the painter s style is not, however, related to the choice of physical equipment but comes from the painter s mind. The artist might choose to paint in very short strokes or in some cases might want to use very long, exaggarated strokes. It is also up to the artist to decide how precise the painting should be the painter might want to accentuate some objects in the scene and perhaps make some objects less apparent. Hertzmann s algorithm is able to vary the output style by introducing style parameters using these parameters the artist can alter the visual style of the algorithm s output. Some of these parameters include approximation threshold (T) which controls how closely the output image resembles the original source image; brush size controls the choice of brush sizes in the rendering using very large brush sizes causes the output image to be approximated more coarsely; curvature filter can be used to constrain or exaggarate the brush strokes shape; minimum and maximum stroke lengths set a maximum and minimum length for a stroke e.g. having a maximum strength of 0 pixels for the strokes creates a style that generates pointilistic images. Figure 3 illustrates the effect of changing the brush size. The picture on the left uses a smaller brush stroke size which makes it more accurate. The picture on the right uses bigger brush strokes and is clearly more inaccurate. 8

9 4 DISCUSSION AND FUTURE WORK Although both of the techniques reviewed in this paper are rather good as such, there is still room for improvement. The brush stroke rendering of Litwinowicz s paper is rather primitive. As all the brush strokes are rendered using the same thickness for all the brushes, the output lacks a certain freedom of expression. There are no coarse, exaggerated strokes drawn, rather the output image s brush distribution is too uniform across the image. The fact that all the brush strokes are drawn using straight lines further adds to this problem. Litwinowicz s algorithm is also rather limited when it comes to varying the rendering style in practice, only the brush thickness can be controlled. Hertzmann has a lot more generic brush stroke model when compared to Litwinowicz s work styles can be varied, the brush strokes are long and curvy and rendered in different sizes. However, Hertzmann s technique does not properly handle animation. If applied to an animation sequence, the technique would suffer from bad scintillation artifacts due to the lack of frame-to-frame coherence treatment. The algorithm produces mediocre quality animation if the frame rate is lowered to approximately Hz but at higher frame rates the output starts to flicker as the viewer expects a certain continuity in the animation. At lower frame rates the discontinuities become less apparant to the viewer. Hertzmann s later work addresses this problem (Hertzmann & Perlin, 2000). In this paper he extends his previous painting technique by using optical flow to warp the brush strokes across multiple frames in an image sequence. The optical flow is used in a manner similar to Litwinowicz s work. Both of the techniques presented in this paper take only global user parameters, that is, parameters that affect the full output image. An artists might need more detailed, local control over the painterly style for example, parameters that can be used to give more detail to specific areas of the image to emphasize a certain character or an object. This kind of extensions could be easily integrated into Hertzmann s technique. E.g. having a mask image that would for each pixel tell the amount of detail desired. The mask image s value could then be used to control the error parameter T across the picture. Hertzmann has already taken a step towards this in his newer work where he proposes a relaxation procedure that given an energy function, tries to find a set of brush strokes that minimize the energy in the painting (Hertzmann, 2000). It would also be interesting to see painterly rendering in real-time applications. Algorithms have been presented on the pen-and-ink side that are fast enough to be used in real-time applications (Markosian et al., 1997). Meier s painterly rendering algorithm can also run at animation frame rates. However, applying either Litwinowicz s or Hertzmann s algorithms to real-time applications seems impractical for animation, both techniques require the use of optical flow which is computationally very expensive to calculate. The performance of the actual brush stroke computation can be further optimized, e.g. through the use of summed area tables in the filtering process. 9

10 REFERENCES Adobe Systems Adobe Photoshop 4.0. Burt Peter J., & Adelson Edward H The Laplacian Pyramid as a Compact Image Code. IEEE Transactions on Communications, Curtis Cassidy, Anderson Sean, Seims Joshua, Fleischer Kurt, & Salesin David H Computer-Generated Watercolor. SIGGRAPH 97 Conference Proceedings, Haeberli Paul Paint By Numbers: Abstract Image Representations. SIGGRAPH Annual Conference Proceedings, Hertzmann Aaron Painterly Rendering with Curved Brush Strokes of Multiple Sizses. SIGGRAPH 98 Conference Proceedings, Hertzmann Aaron Paint by Relaxation. Hertzmann Aaron, & Perlin Ken Painterly Rendering for Video and Interaction. First Internationl Symposium on Non-Photorealistic Animation and Rendering. Igarashi Takeo, Matsuoka Satoshi, & Tanaka Hidehiko Teddy: A Sketching Interface for 3D Freeform Design. SIGGRAPH 99 Conference Proceedings, Kaplan Craig S., & Salesin David H Escherization. SIGGRAPH 2000 Conference Proceedings, Litwinowicz Peter Processing Images and Video for An Impressionist Effect. SIGGRAPH 97 Conference Proceedings, Markosian Lee, Kowalski Michael A., Trychin Samuel J., Bourdev Lubomir D., Goldstein Daniel, & Hughes John F Real-time nonphotorealistic rendering. SIGGRAPH 97 Conference Proceedings, Meier Barbara Painterly Rendering for Animation. SIGGRAPH 96 Conference Proceedings, Salisbury Michael, Wong Michael, Hughes John, & Salesin David Orientable Textures for Image-Based Pen-and-Ink Illustration. SIGGRAPH 97 Conference Proceedings, Sonka Milan, Hlavac Vaclav, & Boyle Roger Image Processing, Analysis and Machine Vision Strassman S Hairy brushes. SIGGRAPH 86,

11 Treavett F., & M. Chen Statistical Techniques for the Automated Synthesis of Non-Photorealistic Images. Proc. 15th Eurographics UK Conference. 11

NPR. CS 334 Non-Photorealistic Rendering. Daniel G. Aliaga

NPR. CS 334 Non-Photorealistic Rendering. Daniel G. Aliaga NPR CS 334 Non-Photorealistic Rendering Daniel G. Aliaga 3D Computer Graphics Today Miraculous performance leaps Stunning price cuts Curiously low impact Games Movies * Slides courtesy of Lee Markosian

More information

Non-Photorealistic Rendering

Non-Photorealistic Rendering 15-462 Computer Graphics I Lecture 22 Non-Photorealistic Rendering November 18, 2003 Doug James Carnegie Mellon University http://www.cs.cmu.edu/~djames/15-462/fall03 Pen-and-Ink Illustrations Painterly

More information

Types of Computer Painting

Types of Computer Painting Painterly Rendering Types of Computer Painting Physical simulation User applies strokes Computer simulates media (e.g. watercolor on paper) Automatic painting User provides input image or 3D model and

More information

Real-time non-photorealistic rendering

Real-time non-photorealistic rendering Real-time non-photorealistic rendering Lauri Siljamäki HUT Lauri.Siljamaki@hut.fi Abstract This paper summarizes techniques used for real-time non-photorealistic rendering (NPR). Currently most NPR images

More information

Nonphotorealistic Virtual Environment Navigation from Images

Nonphotorealistic Virtual Environment Navigation from Images Nonphotorealistic Virtual Environment Navigation from Images Hyung W. Kang Department of Mathematics and Computer Science University of Missouri - St. Louis One University Blvd. St. Louis, MO 63121, USA

More information

View-Dependent Particles for Interactive Non-Photorealistic Rendering

View-Dependent Particles for Interactive Non-Photorealistic Rendering View-Dependent Particles for Interactive Non-Photorealistic Rendering Research Paper 1 Abstract We present a novel framework for non-photorealistic rendering based on view-dependent geometric simplification

More information

CS559: Computer Graphics. Lecture 6: Painterly Rendering and Edges Li Zhang Spring 2008

CS559: Computer Graphics. Lecture 6: Painterly Rendering and Edges Li Zhang Spring 2008 CS559: Computer Graphics Lecture 6: Painterly Rendering and Edges Li Zhang Spring 2008 So far Image formation: eyes and cameras Image sampling and reconstruction Image resampling and filtering Today Painterly

More information

Artistic Stylization of Images and Video

Artistic Stylization of Images and Video Artistic Stylization of Images and Video Eurographics 2011 John Collomosse and Jan Eric Kyprianidis Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey, United Kingdom Hasso-Plattner-Institut,

More information

Rendering Nonphotorealistic Strokes with Temporal and Arc-Length Coherence

Rendering Nonphotorealistic Strokes with Temporal and Arc-Length Coherence -.,., Rendering Nonphotorealistic Strokes with Temporal and Arc-Length Coherence Lubomir Bourdev Department of Computer Science Brown University Submitted in partial fulfillment of the requirements for

More information

View-Dependent Particles for Interactive Non-Photorealistic Rendering

View-Dependent Particles for Interactive Non-Photorealistic Rendering View-Dependent Particles for Interactive Non-Photorealistic Rendering Derek Cornish 1, Andrea Rowan 2, David Luebke 2 1 2 Intrinsic Graphics University of Virginia Abstract We present a novel framework

More information

Real-Time Charcoal Rendering Using Contrast Enhancement Operators

Real-Time Charcoal Rendering Using Contrast Enhancement Operators Real-Time Charcoal Rendering Using Contrast Enhancement Operators Aditi Majumder and M. Gopi Department of Computer Science University of North Carolina at Chapel Hill fmajumder,gopig@cs.unc.edu Abstract.

More information

Real-Time Painterly Rendering for MR Applications

Real-Time Painterly Rendering for MR Applications Real-Time Painterly Rendering for MR Applications Michael Haller Upper Austria University of Applied Sciences Media Technology and Design, Austria Daniel Sperl Upper Austria University of Applied Sciences

More information

Paint by Numbers and Comprehensible Rendering of 3D Shapes

Paint by Numbers and Comprehensible Rendering of 3D Shapes Paint by Numbers and Comprehensible Rendering of 3D Shapes Prof. Allison Klein Announcements Sign up for 1 st presentation at end of class today Undergrads: Thinking about grad school? Still here over

More information

Making Impressionist Paintings Out of Real Images

Making Impressionist Paintings Out of Real Images Making Impressionist Paintings Out of Real Images Aditya Joshua Batra December 13, 2017 Abstract In this project, I have used techniques similar to those used by Patrick Callahan [1] and Peter Litwinowicz

More information

Synthesis of Oil-Style Paintings

Synthesis of Oil-Style Paintings Synthesis of Oil-Style Paintings Fay Huang (B), Bo-Hui Wu, and Bo-Ru Huang Department of Computer Science and Information Engineering, National Ilan University, Yi-lan, Taiwan, ROC fay@niu.edu.tw Abstract.

More information

INSPIRE: An Interactive Image Assisted Non-Photorealistic Rendering System

INSPIRE: An Interactive Image Assisted Non-Photorealistic Rendering System INSPIRE: An Interactive Image Assisted Non-Photorealistic Rendering System Minh X. Nguyen Hui Xu Xiaoru Yuan Baoquan Chen Department of Computer Science and Engineering University of Minnesota at Twin

More information

THE combination of Darwin s theory and computer graphics

THE combination of Darwin s theory and computer graphics Evolved Strokes in Non Photo Realistic Rendering Ashkan Izadi,Vic Ciesielski School of Computer Science and Information Technology RMIT University, Melbourne, 3000, VIC, Australia {ashkan.izadi,vic.ciesielski}@rmit.edu.au

More information

Preprint draft: to appear in ACM SIGGRAPH do not distribute. Real-Time Hatching

Preprint draft: to appear in ACM SIGGRAPH do not distribute. Real-Time Hatching Real-Time Hatching Emil Praun Hugues Hoppe Matthew Webb Adam Finkelstein Princeton University Microsoft Research Princeton University Princeton University Abstract Drawing surfaces using hatching strokes

More information

Artistic Rendering of Function-based Shape Models

Artistic Rendering of Function-based Shape Models Artistic Rendering of Function-based Shape Models by Shunsuke Suzuki Faculty of Computer and Information Science Hosei University n00k1021@k.hosei.ac.jp Supervisor: Alexander Pasko March 2004 1 Abstract

More information

VIRTUAL PAINTING: MODEL AND RESULTS

VIRTUAL PAINTING: MODEL AND RESULTS ICCVG 2002 Zakopane, 25-29 Sept. 2002 Dominique SOBCZYK 1, Vincent BOYER 2, Jean-Jacques BOURDIN 3 1,2,3 G.R.I.S., Laboratoire d Intelligence Artificielle, Université Paris 8, France 1 dom@ai.univ-paris8.fr

More information

Art Based Rendering of Fur by Instancing Geometry

Art Based Rendering of Fur by Instancing Geometry Art Based Rendering of Fur by Instancing Geometry Abstract Richie Steigerwald In this paper, I describe a non- photorealistic rendering system that uses strokes to render fur and grass in a stylized manner

More information

A model to blend renderings

A model to blend renderings A model to blend renderings Vincent Boyer and Dominique Sobczyk L.I.A.S.D.-Universit Paris 8 September 15, 2006 Abstract. We propose a model to blend renderings. It consists in mixing different kind of

More information

Photorealism vs. Non-Photorealism in Computer Graphics

Photorealism vs. Non-Photorealism in Computer Graphics The Art and Science of Depiction Photorealism vs. Non-Photorealism in Computer Graphics Fredo Durand MIT- Lab for Computer Science Global illumination How to take into account all light inter-reflections

More information

Non-Photorealistic Rendering (NPR) Christian Richardt, Rainbow Group

Non-Photorealistic Rendering (NPR) Christian Richardt, Rainbow Group Non-Photorealistic Rendering (NPR) Christian Richardt, Rainbow Group Structure in six parts 1. Definition of non-photorealistic rendering (NPR) 2. History of computer graphics: from 1970s to 1995 3. Overview

More information

A Survey of Pen-and-Ink Illustration in Non-photorealistic

A Survey of Pen-and-Ink Illustration in Non-photorealistic A Survey of Pen-and-Ink Illustration in Non-photorealistic Rendering CS361 Computer Science Department GWU Page 1 of 25 Table of Contents A Survey of Pen-and-Ink Illustration in Non-photorealistic Rendering...

More information

Non-photorealistic Rendering

Non-photorealistic Rendering Non-photorealistic Rendering Art Rendering 1 From: ATI Radeon 9700 Real-Time Demos A Brief History of (Western) Painting Prehistoric Egyptian Medieval Renaissance A peak in realism Impressionism Modernism

More information

Non-Photorealistic Experimentation Jhon Adams

Non-Photorealistic Experimentation Jhon Adams Non-Photorealistic Experimentation Jhon Adams Danny Coretti Abstract Photo-realistic rendering techniques provide an excellent method for integrating stylized rendering into an otherwise dominated field

More information

D animation. Advantages of 3-D3. Advantages of 2-D2. Related work. Key idea. Applications of Computer Graphics in Cel Animation.

D animation. Advantages of 3-D3. Advantages of 2-D2. Related work. Key idea. Applications of Computer Graphics in Cel Animation. Applications of Computer Graphics in Cel Animation 3-D D and 2-D 2 D animation Adam Finkelstein Princeton University Homer 3-D3 Homer 2-D2 Advantages of 3-D3 Complex lighting and shading Reuse from scene

More information

Non photorealistic Rendering

Non photorealistic Rendering EECS 487 Non photorealistic Rendering Lee Markosian December 11, 2006 Whether to use photorealism depends on the purpose of the image: Documentation Illustration Story telling Expression Whether to use

More information

Seamless Integration of Stylized Renditions in Computer-Generated Landscape Visualization

Seamless Integration of Stylized Renditions in Computer-Generated Landscape Visualization Seamless Integration of Stylized Renditions in Computer-Generated Landscape Visualization Liviu Coconu 1, Carsten Colditz 2, Hans-Christian Hege 1 and Oliver Deussen 2 Abstract We propose enhancements

More information

Image Precision Silhouette Edges

Image Precision Silhouette Edges Image Precision Silhouette Edges Ramesh Raskar * Michael Cohen + * University of North Carolina at Chapel Hill + Microsoft Research Abstract inding and displaying silhouette edges is important in applications

More information

An Abstraction Technique for Producing 3D Visual Contents

An Abstraction Technique for Producing 3D Visual Contents , pp.353-360 http://dx.doi.org/10.14257/ijmue.2013.8.5.35 An Abstraction Technique for Producing 3D Visual Contents Kyungha Min Dept. of Digital Media, Sangmyung Univ., Seoul, Korea minkyungha@gmail.com

More information

Non photorealistic Rendering

Non photorealistic Rendering EECS 487 Non photorealistic Rendering Lee Markosian April 9, 2007 Whether to use photorealism depends on the purpose of the image: Training/simulation Documentation Illustration Story telling Expression

More information

Motion Estimation. There are three main types (or applications) of motion estimation:

Motion Estimation. There are three main types (or applications) of motion estimation: Members: D91922016 朱威達 R93922010 林聖凱 R93922044 謝俊瑋 Motion Estimation There are three main types (or applications) of motion estimation: Parametric motion (image alignment) The main idea of parametric motion

More information

Moment Based Painterly Rendering Using Connected. Color Components

Moment Based Painterly Rendering Using Connected. Color Components Moment Based Painterly Rendering Using Connected Color Components A thesis submitted in partial fulfilment of the requirements for the degree of Master of Science in Computer Science and Software Engineering

More information

Painterly Rendering Framework from Composition

Painterly Rendering Framework from Composition Painterly Rendering Framework from Composition Chi Chu Department of Computer Science National Chiao Tung University 1001 Ta Hsueh Rd., Hsinchu, Taiwan 300, R.O.C maktub.cs94g@nctu.edu.tw Zen-Chung Shih

More information

Nonphotorealism. Christian Miller CS Fall 2011

Nonphotorealism. Christian Miller CS Fall 2011 Nonphotorealism Christian Miller CS 354 - Fall 2011 Different goals Everything we ve done so far has been working (more or less) towards photorealism But, you might not want realism as a stylistic choice

More information

Artistic Stylization of Images and Video Part III Anisotropy and Filtering Eurographics 2011

Artistic Stylization of Images and Video Part III Anisotropy and Filtering Eurographics 2011 Artistic Stylization of Images and Video Part III Anisotropy and Filtering Eurographics 2011 Hasso-Plattner-Institut, University of Potsdam, Germany Image/Video Abstraction Stylized Augmented Reality for

More information

Real-Time Hatching. Abstract. 1 Introduction

Real-Time Hatching. Abstract. 1 Introduction Real-Time Hatching Emil Praun Hugues Hoppe Matthew Webb Adam Finkelstein Princeton University Microsoft Research Princeton University Princeton University Abstract Drawing surfaces using hatching strokes

More information

Nonphotorealistic rendering

Nonphotorealistic rendering Nonphotorealistic rendering Photorealism Computational Photography, 6.882 Bill Freeman Fredo Durand May 9, 2006 Physically realistic computer graphics rendering Images with photographic quality (eg Vermeer,

More information

TSP Art. Craig S. Kaplan School of Computer Science University of Waterloo

TSP Art. Craig S. Kaplan School of Computer Science University of Waterloo TSP Art Craig S. Kaplan School of Computer Science University of Waterloo csk@cgl.uwaterloo.ca Robert Bosch Department of Mathematics Oberlin College bobb@cs.oberlin.edu Abstract Bosch and Herman recently

More information

Stylized Video Cubes. Allison W. Klein 1 Peter-Pike J. Sloan 2 Adam Finkelstein 1 Michael F. Cohen 2. Abstract. 1 Introduction

Stylized Video Cubes. Allison W. Klein 1 Peter-Pike J. Sloan 2 Adam Finkelstein 1 Michael F. Cohen 2. Abstract. 1 Introduction Stylized Video Cubes Allison W. Klein 1 Peter-Pike J. Sloan 2 Adam Finkelstein 1 Michael F. Cohen 2 1 Princeton University 2 Microsoft Research Abstract We present a new set of non-photorealistic rendering

More information

CSCI 4972/6963 Advanced Computer Graphics Quiz 2 Tuesday April 17, 2007 noon-1:30pm

CSCI 4972/6963 Advanced Computer Graphics Quiz 2 Tuesday April 17, 2007 noon-1:30pm CSCI 4972/6963 Advanced Computer Graphics Quiz 2 Tuesday April 17, 2007 noon-1:30pm Name: RCS username: This quiz is closed book & closed notes except for one 8.5x11 (double-sided) sheet of notes. Please

More information

A Qualitative Analysis of 3D Display Technology

A Qualitative Analysis of 3D Display Technology A Qualitative Analysis of 3D Display Technology Nicholas Blackhawk, Shane Nelson, and Mary Scaramuzza Computer Science St. Olaf College 1500 St. Olaf Ave Northfield, MN 55057 scaramum@stolaf.edu Abstract

More information

Simulation and Rendering of Opus Palladium 3D Mosaics

Simulation and Rendering of Opus Palladium 3D Mosaics Simulation and Rendering of Opus Palladium 3D Mosaics Vladimir Alves dos Passos and Marcelo Walter Centro de Informática - UFPE, Brazil Abstract Mosaic sculptures are a form of art where the sculpture

More information

I d like to start this section with a quote from David Byrne in an article for Utne. In the article he was mostly talking about 2D design and

I d like to start this section with a quote from David Byrne in an article for Utne. In the article he was mostly talking about 2D design and 1 I d like to start this section with a quote from David Byrne in an article for Utne. In the article he was mostly talking about 2D design and illustration, but I believe his point translates to renderings

More information

Painterly rendering with contentdependent natural paint strokes. Hua Huang, Tian-Nan Fu & Chen-Feng Li

Painterly rendering with contentdependent natural paint strokes. Hua Huang, Tian-Nan Fu & Chen-Feng Li Painterly rendering with contentdependent natural paint strokes Hua Huang, Tian-Nan Fu & Chen-Feng Li The Visual Computer International Journal of Computer Graphics ISSN 0178-2789 Volume 27 Number 9 Vis

More information

CMSC 491A/691A Artistic Rendering. Artistic Rendering

CMSC 491A/691A Artistic Rendering. Artistic Rendering CMSC 491A/691A Artistic Rendering Penny Rheingans UMBC Artistic Rendering Computer-generated images in a style similar to some artistic media or style Also called non-photorealistic rendering (NPR) Different

More information

Stylizing 2.5-D Video

Stylizing 2.5-D Video Stylizing 2.5-D Video Noah Snavely University of Washington C. Lawrence Zitnick Microsoft Research Sing Bing Kang Microsoft Research Michael Cohen Microsoft Research Figure 1: Non-photorealistic rendering

More information

12/3/2007. Non-Photorealistic Rendering (NPR) What is NPR exactly? What is NPR exactly? What is NPR exactly? What is NPR exactly?

12/3/2007. Non-Photorealistic Rendering (NPR) What is NPR exactly? What is NPR exactly? What is NPR exactly? What is NPR exactly? Non-Photorealistic Rendering (NPR) aka. Stylized rendering, artistic rendering, expressive graphics Covers any area of graphics where the point is to consciously not produce an image that is as photorealistic

More information

Video Painting based on a Stabilized 3D Flow Field

Video Painting based on a Stabilized 3D Flow Field TO APPEAR IN IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS Video Painting based on a Stabilized 3D Flow Field Jong-Chul Yoon In-Kwon Lee Henry Kang Abstract We present a method for generating

More information

3 NON-PHOTOREALISTIC RENDERING FOR OUTDOOR SCENE Irene Liew Suet Fun Mohd Shahrizal Sunar

3 NON-PHOTOREALISTIC RENDERING FOR OUTDOOR SCENE Irene Liew Suet Fun Mohd Shahrizal Sunar 3 NON-PHOTOREALISTIC RENDERING FOR OUTDOOR SCENE Irene Liew Suet Fun Mohd Shahrizal Sunar INTRODUCTION A dvance rendering technique in computer graphics include non-photorealitstic rendering. Non-photorealistic

More information

Artistic Silhouettes: A Hybrid Approach

Artistic Silhouettes: A Hybrid Approach Artistic Silhouettes: A Hybrid Approach J.D. Northrup and Lee Markosian Brown University, Providence, RI 02912 Abstract We present a new algorithm for rendering silhouette outlines of 3D polygonal meshes

More information

Panoramic Image Stitching

Panoramic Image Stitching Mcgill University Panoramic Image Stitching by Kai Wang Pengbo Li A report submitted in fulfillment for the COMP 558 Final project in the Faculty of Computer Science April 2013 Mcgill University Abstract

More information

Fine Tone Control in Hardware Hatching

Fine Tone Control in Hardware Hatching Fine Tone Control in Hardware Hatching Matthew Webb Emil Praun Adam Finkelstein Hugues Hoppe Princeton University Princeton University Princeton University Microsoft Research Figure 1: Bunny rendered using

More information

Synthesizing Non Photo-Realistic Rendering Effects of Volumetric Strokes

Synthesizing Non Photo-Realistic Rendering Effects of Volumetric Strokes JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 28, 521-535 (2012) Synthesizing Non Photo-Realistic Rendering Effects of Volumetric Strokes LIEU-HEN CHEN, YI-HSIEN CHEN, SHUO-YAN LIN, TING-YU LIU AND WEN-CHIEN

More information

How to draw and create shapes

How to draw and create shapes Adobe Flash Professional Guide How to draw and create shapes You can add artwork to your Adobe Flash Professional documents in two ways: You can import images or draw original artwork in Flash by using

More information

CS4495 Fall 2014 Computer Vision Problem Set 5: Optic Flow

CS4495 Fall 2014 Computer Vision Problem Set 5: Optic Flow CS4495 Fall 2014 Computer Vision Problem Set 5: Optic Flow DUE: Wednesday November 12-11:55pm In class we discussed optic flow as the problem of computing a dense flow field where a flow field is a vector

More information

Simple Silhouettes for Complex Surfaces

Simple Silhouettes for Complex Surfaces Eurographics Symposium on Geometry Processing(2003) L. Kobbelt, P. Schröder, H. Hoppe (Editors) Simple Silhouettes for Complex Surfaces D. Kirsanov, P. V. Sander, and S. J. Gortler Harvard University Abstract

More information

CS452/552; EE465/505. Finale!

CS452/552; EE465/505. Finale! CS452/552; EE465/505 Finale! 4-23 15 Outline! Non-Photorealistic Rendering! What s Next? Read: Angel, Section 6.11 Nonphotorealistic Shading Color Plate 11 Cartoon-shaded teapot Final Exam: Monday, April

More information

OLE Coordinate System: Subjective Motion for Interactive Optical Illusion

OLE Coordinate System: Subjective Motion for Interactive Optical Illusion OLE Coordinate System: Subjective Motion for Interactive Optical Illusion Jun Fujiki Graduate School of Design Taketoshi Ushiama Faculty of Design Reiji Tsuruno Faculty of Design Kiyoshi Tomimatsu Faculty

More information

Sketchy Shade Strokes

Sketchy Shade Strokes Sketchy Shade Strokes Carl Johan Sörman Jens Hult Department of Computer Science University of Gothenburg 2005 Abstract. As a contribution to the world of Non-Photorealistic Rendering, we present an algorithm

More information

Employing Approximate 3D Models to Enrich Traditional Computer Assisted Animation

Employing Approximate 3D Models to Enrich Traditional Computer Assisted Animation Copyright c 2002 Institute of Electrical and Electronics Engineers, Inc. All rights reserved. 1 Employing Approximate 3D Models to Enrich Traditional Computer Assisted Animation Fabian Di Fiore Frank Van

More information

Effectiveness of Silhouette Rendering Algorithms in Terrain Visualisation

Effectiveness of Silhouette Rendering Algorithms in Terrain Visualisation Effectiveness of Silhouette Rendering Algorithms in Terrain Visualisation Ruzinoor bin Che Mat Sekolah Teknologi Maklumat Universiti Utara Malaysia 06010 Sintok, Kedah Darulaman. Malaysia. ruzinoor@uum.edu.my

More information

Object Removal Using Exemplar-Based Inpainting

Object Removal Using Exemplar-Based Inpainting CS766 Prof. Dyer Object Removal Using Exemplar-Based Inpainting Ye Hong University of Wisconsin-Madison Fall, 2004 Abstract Two commonly used approaches to fill the gaps after objects are removed from

More information

Image Precision Silhouette Edges

Image Precision Silhouette Edges Image Precision Silhouette Edges by Ramesh Raskar and Michael Cohen Presented at I3D 1999 Presented by Melanie Coggan Outline Motivation Previous Work Method Results Conclusions Outline Motivation Previous

More information

CS334: Digital Imaging and Multimedia Edges and Contours. Ahmed Elgammal Dept. of Computer Science Rutgers University

CS334: Digital Imaging and Multimedia Edges and Contours. Ahmed Elgammal Dept. of Computer Science Rutgers University CS334: Digital Imaging and Multimedia Edges and Contours Ahmed Elgammal Dept. of Computer Science Rutgers University Outlines What makes an edge? Gradient-based edge detection Edge Operators From Edges

More information

Edge Detection (with a sidelight introduction to linear, associative operators). Images

Edge Detection (with a sidelight introduction to linear, associative operators). Images Images (we will, eventually, come back to imaging geometry. But, now that we know how images come from the world, we will examine operations on images). Edge Detection (with a sidelight introduction to

More information

Let s start with occluding contours (or interior and exterior silhouettes), and look at image-space algorithms. A very simple technique is to render

Let s start with occluding contours (or interior and exterior silhouettes), and look at image-space algorithms. A very simple technique is to render 1 There are two major classes of algorithms for extracting most kinds of lines from 3D meshes. First, there are image-space algorithms that render something (such as a depth map or cosine-shaded model),

More information

Non-Photo Realistic Rendering. Jian Huang

Non-Photo Realistic Rendering. Jian Huang Non-Photo Realistic Rendering Jian Huang P and NP Photo realistic has been stated as the goal of graphics during the course of the semester However, there are cases where certain types of non-photo realistic

More information

Fluid Simulation as a Tool for Painterly Animation

Fluid Simulation as a Tool for Painterly Animation Fluid Simulation as a Tool for Painterly Animation Sven C. Olsen Swarthmore College Bruce A. Maxwell Swarthmore College Abstract In this paper we combine recent work from two different subfields of computer

More information

Autonomous Flock Brush for Non-Photorealistic Rendering

Autonomous Flock Brush for Non-Photorealistic Rendering Autonomous Flock Brush for Non-Photorealistic Rendering Hsueh En Huang, Yew-Soon Ong, Xianshun Chen Centre for Computational Intelligence School of Computer Engineering, Nanyang Technological University

More information

History of computer graphics

History of computer graphics Ivan Sutherland (1963) - SKETCHPAD History of computer graphics CS 248 - Introduction to Computer Graphics Autumn quarter, 2006 Slides for September 26 lecture pop-up menus constraint-based drawing hierarchical

More information

Practice Exam Sample Solutions

Practice Exam Sample Solutions CS 675 Computer Vision Instructor: Marc Pomplun Practice Exam Sample Solutions Note that in the actual exam, no calculators, no books, and no notes allowed. Question 1: out of points Question 2: out of

More information

Mosaics. Today s Readings

Mosaics. Today s Readings Mosaics VR Seattle: http://www.vrseattle.com/ Full screen panoramas (cubic): http://www.panoramas.dk/ Mars: http://www.panoramas.dk/fullscreen3/f2_mars97.html Today s Readings Szeliski and Shum paper (sections

More information

Adobe Photoshop CS5 Advanced. Course Outline. Course Length: 1 Day. Course Overview

Adobe Photoshop CS5 Advanced. Course Outline. Course Length: 1 Day. Course Overview Adobe Photoshop CS5 Advanced Course Length: 1 Day Course Overview Photoshop CS5: Advanced is the second of three titles in this series. In this course, students will learn how to use color fills, gradients,

More information

Physically-Based Laser Simulation

Physically-Based Laser Simulation Physically-Based Laser Simulation Greg Reshko Carnegie Mellon University reshko@cs.cmu.edu Dave Mowatt Carnegie Mellon University dmowatt@andrew.cmu.edu Abstract In this paper, we describe our work on

More information

A Keypoint Descriptor Inspired by Retinal Computation

A Keypoint Descriptor Inspired by Retinal Computation A Keypoint Descriptor Inspired by Retinal Computation Bongsoo Suh, Sungjoon Choi, Han Lee Stanford University {bssuh,sungjoonchoi,hanlee}@stanford.edu Abstract. The main goal of our project is to implement

More information

CSE328 Fundamentals of Computer Graphics: Concepts, Theory, Algorithms, and Applications

CSE328 Fundamentals of Computer Graphics: Concepts, Theory, Algorithms, and Applications CSE328 Fundamentals of Computer Graphics: Concepts, Theory, Algorithms, and Applications Hong Qin State University of New York at Stony Brook (Stony Brook University) Stony Brook, New York 11794--4400

More information

Non-Photorealistic Virtual Environments

Non-Photorealistic Virtual Environments Non-Photorealistic Virtual Environments Allison W. Klein Wilmot Li Michael M. Kazhdan Wagner T. Corrêa Adam Finkelstein Thomas A. Funkhouser Princeton University Abstract We describe a system for non-photorealistic

More information

Ink-and-wash Painting Based on the Image of Pine Tree using Mean Curvature Flow

Ink-and-wash Painting Based on the Image of Pine Tree using Mean Curvature Flow Ink-and-wash Painting Based on the Image of Pine Tree using Mean Curvature Flow IkSuk Yang Dept. of Computer Science & Computer Eng. Pusan National University Busan 609-735, Rep. of Korea DoHoon Lee Dept.

More information

Non-photorealistic Rendering Using an Adaptive Halftoning Technique

Non-photorealistic Rendering Using an Adaptive Halftoning Technique Non-photorealistic Rendering Using an Adaptive Halftoning Technique L. Streit O. Veryovka and J. Buchanan Imager group Department of Computer Science The University of British Columbia Vancouver, British

More information

Edge and corner detection

Edge and corner detection Edge and corner detection Prof. Stricker Doz. G. Bleser Computer Vision: Object and People Tracking Goals Where is the information in an image? How is an object characterized? How can I find measurements

More information

In this exercise you will be creating the graphics for the index page of a Website for children about reptiles.

In this exercise you will be creating the graphics for the index page of a Website for children about reptiles. LESSON 2: CREATING AND MANIPULATING IMAGES OBJECTIVES By the end of this lesson, you will be able to: create and import graphics use the text tool attach text to a path create shapes create curved and

More information

Adaptive Point Cloud Rendering

Adaptive Point Cloud Rendering 1 Adaptive Point Cloud Rendering Project Plan Final Group: May13-11 Christopher Jeffers Eric Jensen Joel Rausch Client: Siemens PLM Software Client Contact: Michael Carter Adviser: Simanta Mitra 4/29/13

More information

Mesh Repairing and Simplification. Gianpaolo Palma

Mesh Repairing and Simplification. Gianpaolo Palma Mesh Repairing and Simplification Gianpaolo Palma Mesh Repairing Removal of artifacts from geometric model such that it becomes suitable for further processing Input: a generic 3D model Output: (hopefully)a

More information

Introduction to Computer Graphics

Introduction to Computer Graphics Introduction to 1.1 What is computer graphics? it would be difficult to overstate the importance of computer and communication technologies in our lives. Activities as wide-ranging as film making, publishing,

More information

Advanced Real- Time Cel Shading Techniques in OpenGL Adam Hutchins Sean Kim

Advanced Real- Time Cel Shading Techniques in OpenGL Adam Hutchins Sean Kim Advanced Real- Time Cel Shading Techniques in OpenGL Adam Hutchins Sean Kim Cel shading, also known as toon shading, is a non- photorealistic rending technique that has been used in many animations and

More information

Non-Photorealistic Rendering: From a general view to Suggestive contours

Non-Photorealistic Rendering: From a general view to Suggestive contours Non-Photorealistic Rendering: From a general view to Suggestive contours Giorgio Conte and Massimo De Marchi EVL Creative Coding CS 488 - Computer Graphics University of Illinois at Chicago November 2014

More information

Textured Image Based Painterly Rendering Under Arbitrary Lighting

Textured Image Based Painterly Rendering Under Arbitrary Lighting Textured Image Based Painterl Rering Under Arbitrar Lighting George ElKoura Universit of Toronto gelkoura@cs.toronto.edu Abstract Painterl rering stles have received some attention latel as an interesting

More information

AN ABSTRACT OF THE THESIS OF

AN ABSTRACT OF THE THESIS OF AN ABSTRACT OF THE THESIS OF Mizuki Kagaya for the degree of Master of Science in Computer Science presented on May 1, 2009. Title: Painterly Rendering Using Space-Time Varying Style Parameters Abstract

More information

Ink Segmentation. WeeSan Lee Apr 5, 2005

Ink Segmentation. WeeSan Lee Apr 5, 2005 Ink Segmentation WeeSan Lee Apr 5, 2005 Outline Motivation Contribution Background How It Works Conclusion References http://www.cs.ucr.edu/~weesan/smart_tools/ink_segmentation.pdf 2 Motivation Segment

More information

Broad field that includes low-level operations as well as complex high-level algorithms

Broad field that includes low-level operations as well as complex high-level algorithms Image processing About Broad field that includes low-level operations as well as complex high-level algorithms Low-level image processing Computer vision Computational photography Several procedures and

More information

Subdivision Of Triangular Terrain Mesh Breckon, Chenney, Hobbs, Hoppe, Watts

Subdivision Of Triangular Terrain Mesh Breckon, Chenney, Hobbs, Hoppe, Watts Subdivision Of Triangular Terrain Mesh Breckon, Chenney, Hobbs, Hoppe, Watts MSc Computer Games and Entertainment Maths & Graphics II 2013 Lecturer(s): FFL (with Gareth Edwards) Fractal Terrain Based on

More information

Multimedia Technology CHAPTER 4. Video and Animation

Multimedia Technology CHAPTER 4. Video and Animation CHAPTER 4 Video and Animation - Both video and animation give us a sense of motion. They exploit some properties of human eye s ability of viewing pictures. - Motion video is the element of multimedia

More information

Image gradients and edges April 11 th, 2017

Image gradients and edges April 11 th, 2017 4//27 Image gradients and edges April th, 27 Yong Jae Lee UC Davis PS due this Friday Announcements Questions? 2 Last time Image formation Linear filters and convolution useful for Image smoothing, removing

More information

Image gradients and edges April 10 th, 2018

Image gradients and edges April 10 th, 2018 Image gradients and edges April th, 28 Yong Jae Lee UC Davis PS due this Friday Announcements Questions? 2 Last time Image formation Linear filters and convolution useful for Image smoothing, removing

More information

VOLUME PAINTING: INCORPORATING VOLUMETRIC RENDERING WITH LINE INTEGRAL CONVOLUTION (LIC)

VOLUME PAINTING: INCORPORATING VOLUMETRIC RENDERING WITH LINE INTEGRAL CONVOLUTION (LIC) VOLUME PAINTING: INCORPORATING VOLUMETRIC RENDERING WITH LINE INTEGRAL CONVOLUTION (LIC) A Thesis by JAEWOOK LEE Submitted to the Office of Graduate Studies of Texas A&M University in partial fulfillment

More information

PREDICTIVE MODELING FOR 2D FORM DESIGN

PREDICTIVE MODELING FOR 2D FORM DESIGN PREDICTIVE MODELING FOR 2D FORM DESIGN Erhan Batuhan Arisoy, Gunay Orbay, and Levent Burak Kara Department of Mechanical Engineering Carnegie Mellon University Pittsburgh, Pennsylvania 15213 {earisoy,gorbay,lkara}@andrew.cmu.edu

More information

Point based global illumination is now a standard tool for film quality renderers. Since it started out as a real time technique it is only natural

Point based global illumination is now a standard tool for film quality renderers. Since it started out as a real time technique it is only natural 1 Point based global illumination is now a standard tool for film quality renderers. Since it started out as a real time technique it is only natural to consider using it in video games too. 2 I hope that

More information