Hochang Lee

Directional texture transfer

A texture transfer algorithm modifies the target image replacing the high frequency information with the example source image. Previous texture transfer techniques normally use such factors as color distance and standard deviation for selecting the best texture from the candidate sets. These factors are useful for expressing a texture effect of the example source in the target image, but are less than optimal for considering the object shape of the target image. In this paper, we propose a novel texture transfer algorithm to express the directional effect based on the flow of the target image. For this, we use a directional factor that considers the gradient direction of the target image. We add an additional energy term that respects the image gradient to the previous fast texture transfer algorithm. Additionally, we propose a method for estimating the directional factor weight value from the target image. We have tested our algorithm with various target images. Our algorithm can express a result image with the feature of the example source texture and the flow of the target image.

Extended papers from NPAR 2010: Directional texture transfer with edge enhancement

Texture transfer re-renders a target image with high-frequency information (texture) taken from parts of a reference image that is matched locally to the target image using characteristics such as color. In this paper, we add a directional factor based on the flow of the target image, creating a stroke-like effect that follows edges more accurately. In addition, we propose a method to clearly express object boundaries by considering the effect of the medium on edges in the reference image. We also show how to select an appropriate weight for this directional factor from the reference image. We demonstrate the suitability of this improved form of texture transfer for expressing various artistic styles, and compare our results with those from previous texture-transfer algorithms. We find that our algorithm can be adapted to texture synthesis as well.

A multi-level depiction method for painterly rendering based on visual perception cue

Increasing the level of detail (LOD) in brushstrokes within areas of interest improved the realism of painterly rendering. Using a modified quad-tree, we segmented an image into areas with similar levels of saliency; each of these segments was then used to control the brush strokes during rendering. We could also simulate real oil painting steps based on saliency information. Our method runs in a reasonable fine and produces results that are visually appealing and competitive with previous techniques.

Various Artistic Effect Generation From Reference Image

Nowadays smart phone is widely converge and the growth of mobile and small device market is rapidly increasing. And many image based applications are developed for generating contents. In this paper, we propose a system for human-friendly image generation from user chosen reference images. In mobile application research, performance and waiting time is main problems. Because mobile OS is not fast as PC. So we modify previous texture transfer techniques considering waiting time and performance. For this, we modified from scan-line approach to random-access approach. Our proposed system can make various artistic results automatically. From this framework, we develop android operating system based smart phone application. This system can be extended to various imaging devices (IPTV, camera, stylish photo).

Brushstroke Control from Image Saliency

Increasing the level of detail (LOD) in brushstrokes within areas of interest improved the realism of painterly rendering. Using a modified quad-tree, we segmented an image into areas with similar levels of saliency, each of these segments was then used to control the brush strokes during rendering. We could also simulate real oil painting steps based on saliency information. Our method produces results that are visually appealing and good for interactive system.

Stained Glass Rendering with Smooth Tile Boundary

We introduce a new glass tile generation method for simulating Stained Glass using region segmentation algorithm and cubic spline interpolation method. We apply a Mean shift segmentation algorithm to a source image to extract a shape of glass tile. We merge regions by user input and use morphological operation to remove the invalid shape. To make the shape of glass tile, we apply cubic spline interpolation and obtain the leading and the region with smooth boundary. Next, we re-segment the region using the spline curves. Finally we apply the transformed colors to each region to create a whole glass tile.

Simulation of Lenticular Image

Trick art is a genre of artistic expression that can give not only beautifulness but also entertainment. Lenticular image (or printing) is one skill of trick art that shows different image depend on the viewer’s viewpoint by controlling refraction of light. The object, seen by viewer in some view angle, goes shimmering when the viewer change the view angle. In computer graphics area, other trick arts were simulated, but simulation of lenticular image is not well progressed. So in this paper, we do simulate the lenticular Image. For this, we first set the position of input object image on the given background image depend on the similarity of gradient. And then blend the object into background image. Lastly, we cover the lenticular lens on the image that is the composition of original background image and blended image. Finally, we can generate the 3D scene which simulates the lenticular images.

A Novel Color Transfer Algorithm for Impressionistic Paintings

Existing color reproduction algorithms achieve image enhancement or visualization by correcting tone and hue. Although these algorithms are good at incorporating a natural feel in an image, they do not accurately represent intended colors that are contrasted. This limitation is particularly evident in the case of impressionist paintings that have a color contrast based on the style of the painter and the conventions of impressionism. In this study, we propose a novel color reproduction algorithm for impressionism, primarily focusing on paintings by Vincent van Gogh. First, the color value that is most obvious to the user is extracted. Based on this color, the color of the main object is transferred. Then, the color contrast information of a sample painting is extracted based on the color harmony theory. Finally, the color of other regions is transferred. Using our proposed algorithm, a more artistic result that matches the contrast style of the artist is generated. This work should be extended further to enhance the simulation of stroke color by a painterly rendering algorithm.

Painterly Rendering with Focusing Effect

In this paper, we present an algorithm that provides a focusing effect by transforming the character of strokes. The focusing point can be obtained by the density of edges, which refers to the amount of edges in a specific area. After the determination of the focusing point, the following work should be done. First, details and abstraction should be expressed by adjusting the brush size centering on the focusing point. Second, the direction of the brush should be determined so the view is focused through interpolation using the focusing point. Third the focusing point should be exaggerated by adjusting the blur and highlight effects. The focusing effects generated on the desired part through the above procedure can provide an effect of oil painting that has been realized by a human being.