• Title/Summary/Keyword: Tiling technique

Search Result 17, Processing Time 0.021 seconds

High-Speed Generation Technique of Digital holographic Contents based on GPGPU (GPGPU기반의 디지털 홀로그램 콘텐츠의 고속 생성 기법)

  • Lee, Yoon Hyuk;Kim, Dong Wook;Seo, Young Ho
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.9 no.1
    • /
    • pp.151-163
    • /
    • 2013
  • Recently the attention on digital hologram that is regarded as to be the final goal of the 3-dimensional video technology has been increased. Digital hologram is calculated by modeling the interference phenomenon between an object wave and a reference wave. The modeling for digital holograms is called by computer generated hologram (CGH) Generally, CGH requires a very large amount of calculation. So if holograms are generated in real time, high-speed method should be needed. In this paper, we analyzed CGH equation, optimized it for mapping general purpose graphic processing unit (GPGPU), and proposed a optimized CGH calculation technique for GPGPU by resource allocation and various experiments which include block size changing, memory selection, and hologram tiling. The implemented results showed that a digital hologram that has $1,024{\times}1,024$ resolution can be generated during approximately 24ms, using 1K point clouds. In the experiment, we used two GTX 580 GPGPU of nVidia Inc.

Spiral Drawing-based Real-time Crystallization Mosaic Tchnique (나선 드로잉 기반 실시간 결정화 모자이크 기법)

  • Kim, Jae Kyoung;Kim, Young Ho;Park, Jin Wan
    • Journal of the Korean Society for Computer Game
    • /
    • v.31 no.4
    • /
    • pp.137-144
    • /
    • 2018
  • In the past, mosaics were made by laying cloth on the floor and manually tiling the tiles. However, due to recent developments in technology, the data storage method has evolved from analog to digital, so that image representation and conversion can be realized through computer. Also, various expression techniques of mosaic are developed, and it is also used as a method of art representation in digital. There are various studies on the production process of mosaic. The proposed method is a crystallization mosaic that spreads spirally in real time and uses 3D quartz as a tile element. Although existing researches are mostly focused on the purpose of rendering images in more detail, this technique combines untried spiral drawing and crystallization, and attempts to explore new expression techniques in 3D space by attempting a new mosaic method in 3D space. 'Spiral Crystallization Photo', based on this technique, was selected as Top27 in MWU Award 18 and exhibited at Unite Seoul 2018.

Memory data layout and DMA transfer technique research For efficient data transfer of CNN accelerator (CNN 가속기의 효율적인 데이터 전송을 위한 메모리 데이터 레이아웃 및 DMA 전송기법 연구)

  • Cho, Seok-Jae;Park, Sungkyung;Park, Chester Sungchung
    • Journal of IKEEE
    • /
    • v.24 no.2
    • /
    • pp.559-569
    • /
    • 2020
  • One of the deep-running algorithms, CNN's artificial intelligence application uses off-chip memory to store data on the Convolution Layer. DMA can reduce processor load at every data transfer. It can also reduce application performance degradation by varying the order in which data from the Convolution layer is transmitted to the global buffer of the accelerator. For basic layouts with continuous memory addresses, SG-DMA showed about 3.4 times performance improvement in pre-setting DMA compared to using ordinaly DMA, and for Ideal layouts with discontinuous memory addresses, the ordinal DMA was about 1396 cycles faster than SG-DMA. Experiments have shown that a combination of memory data layout and DMA can reduce the DMA preset load by about 86 percent.

A Study on Pointillistic Rendering Based on User Defined Palette (사용자 정의 팔레트에 기반한 점묘화 렌더링에 관한 연구)

  • Seo, Sang-Hyun;Yoon, Kyung-Hyun
    • Journal of Korea Multimedia Society
    • /
    • v.11 no.4
    • /
    • pp.554-565
    • /
    • 2008
  • The French neo-impressionist painter, George Seurat, introduced pointillism under the theory that the individual pigments of colors on the canvas are reconstructed on the human retina. Pointillism is a painting technique in which many small brush strokes are combined to form a picture in the canvas. When such a painting is seen from a far, the individual stroke color are unnoticeable and they are seen as intermixed colors. This is called juxtaposed color mixture. In this paper, we present a painterly rendering method for generating the pointillism images. For expressing countless separate dots which shown in the pointillism works, we propose a hierarchical points structure using Wang The method. Also a user defined palette is constructed based on the usage that Neo-Impressionist painter works on his palette. Lastly, based on this, a probability algorithm will be introduced, which divides the colors in the image(sampled by hierarchical point structure) into juxtaposed colors. A hierarchical points set which undergone juxtaposed color division algorithm is converted into brush strokes.

  • PDF

Improving Performance of ART with Iterative Partitioning using Test Case Distribution Management (테스트 케이스 분포 조절을 통한 IP-ART 기법의 성능 향상 정책)

  • Shin, Seung-Hun;Park, Seung-Kyu;Choi, Kyung-Hee
    • Journal of KIISE:Software and Applications
    • /
    • v.36 no.6
    • /
    • pp.451-461
    • /
    • 2009
  • The Adaptive Random Testing(ART) aims to improve the performance of traditional Random Testing(RT) by reducing the number of test cases to find the failure region which is located in the input domain. Such enhancement can be obtained by efficient selection algorithms of test cases. The ART through Iterative Partitioning(IP-ART) is one of ART techniques and it uses an iterative input domain partitioning method to improve the performance of early-versions of ART which have significant drawbacks in computation time. And the IP-ART with Enlarged Input Domain(EIP-ART), an improved version of IP-ART, is known to make additional performance improvement with scalability by expanding to virtual test space beyond real input domain of IP-ART. The EIP-ART algorithm, however, have the drawback of heavy cost of computation time to generate test cases mainly due to the virtual input domain enlargement. For this reason, two algorithms are proposed in this paper to mitigate the computation overhead of the EIP-ART. In the experiments by simulations, the tiling technique of input domain, one of two proposed algorithms, showed significant improvements in terms of computation time and testing performance.

Rhabdomere Formation in Late Pupal Stage of Drosophila melanogaster; Observation Using High-Pressure Freezing and Freeze-Substitution, and High-Voltage Electron Microscopy (초고압 동결장비와 초고압투과전자현미경을 이용한 초파리의 감간분체 형성과정의 구조분석)

  • Mun, Ji-Young;Arii, Tatsuo;Hama, Kiyoshi;Han, Sung-Sik
    • Applied Microscopy
    • /
    • v.37 no.1
    • /
    • pp.35-42
    • /
    • 2007
  • The late pupal stage of Drosophila melanogaster occurs immediately before the completion of retinal development, during which the rhabdomere rapidly forms. In this period, the photoreceptor cells were fixed and dehydrated using a high-pressure freezer (HPF) and freeze substitution (FS) technique, which is the most effective in preserving the cell structures, and observed using high-voltage electron microscopy (HVEM) at 1000 KV. The rhabdomere was classified structurally into three types of formation patterns using stereo-tiling image of thick sections. Initially, hexagonal arrays of rhabdomere existed in different angles. In addition, small pieces of rhabdomere could be observed in the cytoplasm of the photoreceptor rolls, which were visible during the profess of rhabdomere formation. In addition, multiple layers of rhabdomere strings were observed. We observed there are at least three types of vesicles related to rhabdomere formation in photoreceptor cells. In addition, it was found that these vesicles initiate the formation of the rhabdomeres during the pupal stage. Collectively, these data suggest that rhabdomeres were mainly formed through vesicles, and that parts of the rhabdomere formed first and then gathered and formed rhabdomeres in the late pupal stage.

Efficient 3D Object Simplification Algorithm Using 2D Planar Sampling and Wavelet Transform (2D 평면 표본화와 웨이브릿 변환을 이용한 효율적인 3차원 객체 간소화 알고리즘)

  • 장명호;이행석;한규필;박양우
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.31 no.5_6
    • /
    • pp.297-304
    • /
    • 2004
  • In this paper, a mesh simplification algorithm based on wavelet transform and 2D planar sampling is proposed for efficient handling of 3D objects in computer applications. Since 3D vertices are directly transformed with wavelets in conventional mesh compression and simplification algorithms, it is difficult to solve tiling optimization problems which reconnect vertices into faces in the synthesis stage highly demanding vertex connectivities. However, a 3D mesh is sampled onto 2D planes and 2D polygons on the planes are independently simplified in the proposed algorithm. Accordingly, the transform of 2D polygons is very tractable and their connection information Is replaced with a sequence of vertices. The vertex sequence of the 2D polygons on each plane is analyzed with wavelets and the transformed data are simplified by removing small wavelet coefficients which are not dominant in the subjective quality of its shape. Therefore, the proposed algorithm is able to change the mesh level-of-detail simply by controlling the distance of 2D sampling planes and the selective removal of wavelet coefficients. Experimental results show that the proposed algorithm is a simple and efficient simplification technique with less external distortion.