• The Transactions of the Korea Information Processing Society
• /
• v.6 no.5
• /
• pp.1362-1372
• /
• 1999

Ray-tracing algorithm can synthesize photo-realistic image, but its computational cost is high. Fast image synthesis based on ray-tracing is one of the most important topics in computer graphics. There are two methods for high speed ray-tracing. First this paper discusses various load distribution and scheduling of multiprocessor for high sped ray-tracing. Then this paper proposes load distribution strategies based on them, implements and evaluates it on multiprocessor. The experiment results show that the proposed method can solve the unbalanced load problem of dynamic load distribution, and scan line method and dot method among a kind of static load distribution strategies disperse the load efficiently.

• Korean Journal of Remote Sensing
• /
• v.17 no.4
• /
• pp.335-344
• /
• 2001

Texture is extensively studied in a variety of image processing applications such as image segmentation and classification because it is an important property to perceive regions and surfaces. This paper focused on the analysis and synthesis of textured single and multiband images using Markov Random Field model considering the existent spatial correlation. Especially, for multiband images, the cross-channel correlation existing between bands as well as the spatial correlation within band should be considered in the model. Although a local interaction is assumed between the specified neighboring pixels in MRF models, during the maximization process, short-term correlations among neighboring pixels develop into long-term correlations. This result in exhibiting phase transition. In this research, the role of temperature to obtain the most probable state during the sampling procedure in discrete Markov Random Fields and the stopping rule were also studied.

• Journal of the Optical Society of Korea
• /
• v.12 no.4
• /
• pp.269-274
• /
• 2008

We propose a new synthesis method for the hologram of 3D objects using incoherent multiple orthographic view images. The 3D objects are captured and their multiple orthographic view images are generated from the captured image. Each orthographic view image is numerically overridden by the plane wave propagating in the direction of the corresponding view angle and integrated to form a point in the hologram plane. By repeating this process for all orthographic view images, we can generate the Fourier hologram of the 3D objects.

• International journal of advanced smart convergence
• /
• v.11 no.2
• /
• pp.64-70
• /
• 2022

In recent years, with the continuous innovation and upgrading of engine software, the real-time rendering technology in film and television has been continuously improved, and the virtual production technology has also developed rapidly. This paper introduces the green screen often used in traditional film production and a virtual production technology based on light-emitting-diode background wall that was proposed and implemented last year. We analyzed the two production methods of virtual production and compared their characteristics. Based on these results, we can better understand the differences and respective advantages of the two production methods. And we also can according to the production budget, production cycle and the creative and technical capabilities of the team make better choices during the production process. We believe virtual production technology will be production in the future to provide a more solid technical guarantee for the development of the film industry, and this work will pave the way for further research on virtual production technology.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.95-96
• /
• 2021

본 논문에서는 단안비디오 입력으로부터 각 SAI(sub-aperture image)간의 넓은 기준선을 갖는 라이트필드 합성기법을 제안한다. 기존의 라이트필드 영상은 취득의 어려움에 의해 규모가 작고 특정 물체위주로 구성되어 있어 컴퓨터 비전 및 그래픽스 분야의 최신 딥러닝 기법들을 라이트필드 분야에 적용하기 어렵다는 문제를 갖고 있다. 이러한 문제점들을 해결하기 위해 사실적 렌더링 기반의 가상환경상에서 실제환경과 유사함을 갖는 데이터를 취득하였다. 생성한 데이터셋을 이용하여 기존의 새로운 시점을 생성하는 기법 중 하나인 다중 평면 영상(Multi Plane Image) 기반 합성기법을 통해 라이트필드 영상을 합성한다. 제안하는 네트워크는 단안비디오의 연속된 두개의 프레임으로부터 MPI 추정하는 네트워크와 입력영상의 깊이 정보를 추정하는 네트워크로 구성되어 있다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2021.06a
• /
• pp.105-108
• /
• 2021

Generative adversarial networks (GANs) have reached a great result at creating the synthesis image, especially in the face generation task. Unlike other deep learning tasks, the input of GANs is usually the random vector sampled by a probability distribution, which leads to unstable training and unpredictable output. One way to solve those problems is to employ the label condition in both the generator and discriminator. CelebA and FFHQ are the two most famous datasets for face image generation. While CelebA contains attribute annotations for more than 200,000 images, FFHQ does not have attribute annotations. Thus, in this work, we introduce a method to learn the attributes from CelebA then predict both soft and hard labels for FFHQ. The evaluated result from our model achieves 0.7611 points of the metric is the area under the receiver operating characteristic curve.

• Journal of the Korea Computer Graphics Society
• /
• v.14 no.2
• /
• pp.19-25
• /
• 2008

We synthesize a texture with different structures at different scales. Our technique is based on deterministic parallel synthesis allowing real-time processing on a GPU. A new coordinate transformation operator is used to construct a synthesized coordinate map based on different exemplars at different scales. The runtime overhead is minimal because this operator can be precalculated as a small lookup table. Our technique is effective for upsampling texture-rich images, because the result preserves texture detail well. In addition, a user can design a texture by coloring a low-resolution control image. This design tool can also be used for the interactive synthesis of terrain in the style of a particular exemplar, using the familiar 'raise and lower' airbrush to specify elevation.

• Applied Chemistry for Engineering
• /
• v.28 no.5
• /
• pp.571-575
• /
• 2017

In this study, cadmium telluride (CdTe) quantum dots were synthesized by using ultrasonic irradiation method. Optical properties and structural characteristics of the CdTe quantum dots were analyzed by two main variables; the ratio of the precursor and the synthesis time. As the synthesis time increased, the band gap reduction was observed with the growth of CdTe quantum dots. As for the luminescence properties, the red shift appeared at 510~610 nm wavelength range. Also, it was confirmed that the red shift occurs rapidly as the ratio of Te increases. According to PL peak intensity, the highest intensity was shown at 180 to 240 min. Structural characteristics of CdTe quantum dots were investigated through XRD and TEM, and the cubic zinc blend structure was observed. The size of quantum dots was about 2.5 nm and uniformly dispersed when the synthesis time took 210 min. In addition, the apparent crystallinity was discovered in FFT image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.10B
• /
• pp.1070-1075
• /
• 2009

In this paper, we propose new depth estimation and intermediate view synthesis algorithms for three-dimensional video generation. In order to improve temporal consistency of the depth map sequence, we add a temporal weighting function to the conventional matching function when we compute the matching cost for estimating the depth information. In addition, we propose a boundary noise removal method in the view synthesis operation. after finding boundary noise areas using the depth map, we replace them with corresponding texture information from the other reference image. Experimental results showed that the proposed algorithm improved temporal consistency of the depth sequence and reduced flickering artifacts in the virtual view. It also improved visual quality of the synthesized virtual views by removing the boundary noise.

• Korean Journal of Metals and Materials
• /
• v.50 no.5
• /
• pp.401-406
• /
• 2012

When viewed using a magnetic resonance imaging (MRI) system, invasive materials inside the human body, in many cases, severely distort the MR image of human tissues. The degree of the MR image distortion increases in proportion not only to the difference in the susceptibility between the invasive material and the human tissue, but also to the intensity of the magnetic field induced by the MRI system. In this study, by blending paramagnetic Ti particles with diamagnetic graphite, we synthesized $Ti_{100-x}C_x$ composites that can reduce the artifact in the MR image under the high-strength magnetic field. Of the developed composites, $Ti_{70}C_{30}$ showed the magnetic susceptibility of ${\chi}=67.6{\times}10^{-6}$, which corresponds to 30% of those of commercially available Ti alloys, the lowest reported in the literature. The level of the MR image distortion in the vicinity of the $Ti_{70}C_{30}$ composite insert was nearly negligible even under the high magnetic field of 4.7 T. In this paper, we reported on a methodology of designing new structural materials for bio-applications, their synthesis, experimental confirmation and measurement of MR images.