• Journal of Broadcast Engineering
• /
• v.14 no.2
• /
• pp.164-177
• /
• 2009

The DIBR(depth image-based rendering) method gives the sense of depth to viewers by using one color image and corresponding depth image. At this time, the qualities of the generated left- and right-image depend on the baseline distance of the virtual cameras corresponding to the view of the generated left- and right-image. In this paper, we present a novel method for enhancing the sense of depth by adjusting baseline distance of virtual cameras. Geometric analysis shows that the sense of depth is better in accordance with the increasing disparity due to the reduction of the image distortion. However, the entailed image degradation is not considered. Experimental results show that there is maximum bound in the disparity increasement due to image degradation and the visual field. Since the image degradation is reduced for increasing that bound, we add a depth map preprocessing. Since the interactive service where the disparity and view position are controlled by viewers can also be provided, the proposed method can be applied to the mobile broadcasting system such as DMB as well as 3DTV system.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.2
• /
• pp.1-8
• /
• 2009

This paper introduces a virtual dress up system, according to user's input model and garment image. At first step, we deform the garment image by using skeleton structures and ARAP method. Next step, sampling the boundary points and find their matching vertices which are used for optimizing the boundary fitting. In 2D rendering of the dress up, they have some unrealistic results, so we reconstruct the garment mesh to the 3D mesh. Rendering from the reconstructed 3D mesh, we can get the final dress up result. We present that our system produce a visually plausible and well-fitted virtual dress up results.

• Journal of Biomedical Engineering Research
• /
• v.20 no.3
• /
• pp.283-290
• /
• 1999

Because MR(Magnetic Resonance) slice images have much information of functions about body organs, it is very effeclive for diagnoses lo analyze and visualize MR slice images. A visuahzation process is composed of medical image acquisition, preprocessmg, segmentation, inlerpolation, rendering. Segmentation and interpolation among thenl ,1re currenl hot topics because of MR slice image imperfections. This paper proposes a method for segmentalion, mlerpolation respectively and addresses 3 D-visualizmg of a head. We segmented head tissues uomg otructural knowledge of head studied by clinical experiments sequentially. We improved the dynamic elastic inlerpolation to Utilize in concave conlour. We compared the proposed segmentation method and the interpolation method with other methods.

• Journal of KIBIM
• /
• v.12 no.1
• /
• pp.55-61
• /
• 2022

Recently, demand for designing own space is increasing as the rapid growth of home furnishing market. However, there is a limitation that it is not easy to compare the style between before construction view and after view. This study aims to translate real image into another style with GAN model learned with interior images. To implement this, first we established style criteria and collected modern, natural, and classic style images, and experimented with ResNet, UNet, Gradient penalty concept to CycleGAN algorithm. As a result of training, model recognize common indoor image elements, such as floor, wall, and furniture, and suitable color, material was converted according to interior style. On the other hand, the form of furniture, ornaments, and detailed pattern expressions are difficult to be recognized by CycleGAN model, and the accuracy lacked. Although UNet converted images more radically than ResNet, it was more stained. The GAN algorithm allowed us to represent results within 2 seconds. Through this, it is possible to quickly and easily visualize and compare the front and after the interior space style to be constructed. Furthermore, this GAN will be available to use in the design rendering include interior.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.53-65
• /
• 2012

Existing method of creating Stereoscopy image, creates viewpoint image from the left and right by shooting one object with 2 lens in certain distance. However, in case of 3-D TV using Stereoscopy camera, the necessity to transmit 2 viewpoint images from the left and right simultaneously, increases the amount of bandwidth. Various and more effective alternatives are under discussion. Among the alternatives, DIBR(Depth Image Based Rendering) creates viewpoint images from the left and right using one image and its Depth information, thus decreasing the amount of transmitted bandwidth. For this reason, there have been various studies on Algorithm to create DIBR Image in existing Static Scene. In this paper, I would like to suggest Gaussian Hole-filling solution, which utilizes reverse-depth image to fill the hole naturally, while minimizing distortion of background. In addition, we have analyzed the effectiveness of each Algorithm by comparing and calculating its functions.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.1113-1119
• /
• 2006

본 논문에서는 광고나 포스터제작에 사용될 수 있는 이미지 모자이크 기법을 소개한다. 모자이크는 임의의 개수의 셀로 하나의 전체 이미지를 표현하는 기법이다. 이중 포토 모자이크는 사진의 조합으로 새로운 사진을 생성한다. 이는 만들고자 하는 영상을 격자를 이용해 나누고 해당 격자에 최적의 이미지를 영상 DB 로부터 찾아 격자를 채움으로써 하나의 이미지 모자이크를 생성한다. 본 논문에서는 하나의 단위 이미지(색이 할당되지 않고 형태만 갖는 영상)를 사용하여 경계로 구분된 특정 영역을 채워나감으로써 하나의 추상화된 예술적 모자이크 영상을 생성하는 알고리즘을 소개한다. 하나의 단위 이미지는 회전, 이동을 통해 다양하게 변할 수 있으며 입력영상의 그래디언트의 방향과 에지정보를 이용해 해당영역을 채우게 된다. 이를 위해서 에지를 넘어서지 않도록 단위 이미지를 변환시키며 최적의 위치를 찾게된다. 또한 입력영상의 색상이나 임의의 색상이나 특정 색상테이블을 이용해 단위 이미지에 색상을 할당함으로써 만들고자 하는 입력영상과 비슷한 모양을 갖거나 형태만을 유지한 추상화된 모자이크 영상 생성이 가능하다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.223-226
• /
• 2000

Currently a multichannel system for virtual 3-D sound rendering is under development. Robust sound image formation and smooth real time interactivity are main design Points. The system utilizes VBAP algorithm as virtual sound image positioning. Overall system settings can be easily configured. We developed software, RIMA. as a driving Program of the system. At this stage, it is possible to position virtual sound images at arbitrary positions in three-dimensional space. The characteristics of the system are discussed. The system has been applied to the KAIST Bicycle Simulator to generate the virtual sound field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.7
• /
• pp.1311-1328
• /
• 2011

We re-render a photographic image as a simulated pencil drawing using two independent line integral convolution (LIC) algorithms that express tone and feature lines. The LIC for tone is then applied in the same direction across the image, while the LIC for features is applied in pixels close to each feature line in the direction of that line. Features are extracted using the coherent line scheme. Changing the direction and range of the LICs allows a wide range of pencil drawing style to be mimicked. We tested our algorithm on diverse images and obtained encouraging results.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.459-462
• /
• 2009

Hatching is an effective artistic tool for conveying shape and shading by placing parallel line strokes on drawing objects. We present a simple and effective per-pixel image-space hatching method to draw line strokes using given stroke directions. Our hatching method directly runs on the screen and it can efficiently render highly complex scenes in hatching styles. We implement the algorithm using a pixel shader in a modern GPU.

• Journal of Korea Multimedia Society
• /
• v.14 no.12
• /
• pp.1528-1535
• /
• 2011

We present a fog generation algorithm in 2D images. The proposed algorithm provides a scattering model for the approximated calculation of fog density. The scattering model needs parameters of distance and altitude information. However, 2D images do not include that information, so that we calculate them from the depth information generated in an interactive manner, and estimate the scattering factor by using the scattering model. Then we generate fog effect on an input image using the scattering factor by distance-oriented selection blur and color blending. With the algorithm, we can easily create the fog-effected images and fog generated animation from 2D images.