3DCGiRAM: An intelligent memory architecture for photo-realistic image synthesis

被引:2
|
作者
Kobayashi, H [1 ]
Suzuki, K [1 ]
Sano, K [1 ]
Kaeriyama, Y [1 ]
Saida, Y [1 ]
Oba, N [1 ]
Nakamura, T [1 ]
机构
[1] Tohoku Univ, Sendai, Miyagi 980, Japan
关键词
D O I
10.1109/ICCD.2001.955066
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This paper proposes an intelligent memory architecture for photo-realistic image synthesis, named 3DCGiRAM. The 3DCGiRAM has a hardware-accelerated 3D line generator, which finds objects that are likely to intersect traced rays. It also has functional memory cells, each of which is composed of graphics logic and its local memory to detect intersecting objects and to calculate intensities. A distributed frame buffer is employed to alleviate the access conflicts of functional cells to the frame buffer as well as to compose globally illuminated intensities at screen pixels. As the graphics processing capability is localized to data in the 3DCGiRAM through memory-logic merged LSI technology, a scalability and modularity similar to those of conventional memory modules can be expected. The experimental results show that a single 3DCGiRAM module running at 200MHz with a memory bandwidth of 6.4GB will be able to synthesize a ray-traced walk-through animation at a rate of one frame per second.
引用
收藏
页码:462 / 467
页数:6
相关论文
共 50 条
  • [1] Photo-Realistic Facial Details Synthesis From Single Image
    Chen, Anpei
    Chen, Zhang
    Zhang, Guli
    Mitchell, Kenny
    Yu, Jingyi
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 9428 - 9438
  • [2] Photo-realistic facial expression synthesis
    Ghent, J
    McDonald, J
    IMAGE AND VISION COMPUTING, 2005, 23 (12) : 1041 - 1050
  • [3] Automatic generation of photo-realistic mosaic image
    Park, JS
    Chang, DH
    Park, SG
    BIOLOGICALLY MOTIVATED COMPUTER VISION, PROCEEDING, 2000, 1811 : 343 - 352
  • [4] Photo-realistic image synthesis from lines and appearance with modular modulation
    Luo, Wuyang
    Yang, Su
    Zhang, Weishan
    NEUROCOMPUTING, 2022, 503 : 81 - 91
  • [5] Image-based photo hulls for fast and photo-realistic new view synthesis
    Slabaugh, GG
    Schafer, RW
    Hans, MC
    REAL-TIME IMAGING, 2003, 9 (05) : 347 - 360
  • [6] PAINT: Photo-realistic Fashion Design Synthesis
    Gu, Xiaoling
    Huang, Jie
    Wong, Yongkang
    Yu, Jun
    Fan, Jianping
    Peng, Pai
    Kankanhalli, Mohan S.
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2024, 20 (02)
  • [7] StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks
    Zhang, Han
    Xu, Tao
    Li, Hongsheng
    Zhang, Shaoting
    Wang, Xiaogang
    Huang, Xiaolei
    Metaxas, Dimitris
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 5908 - 5916
  • [8] Image-based rendering for photo-realistic visualization
    Verbiest, F.
    Willems, G.
    van Gool, L.
    VIRTUAL AND PHYSICAL PROTOTYPING, 2006, 1 (01) : 19 - 30
  • [9] Toward Interactive Modulation for Photo-Realistic Image Restoration
    Cai, Haoming
    He, Jingwen
    Qiao, Yu
    Dong, Chao
    2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021, 2021, : 294 - 303
  • [10] Photo-Realistic Expressive Text to Talking Head Synthesis
    Wan, Vincent
    Anderson, Robert
    Blokland, Art
    Braunschweiler, Norbert
    Chen, Langzhou
    Kolluru, BalaKrishna
    Latorre, Javier
    Maia, Ranniery
    Stenger, Bjoern
    Yanagisawa, Kayoko
    Stylianou, Yannis
    Akamine, Masami
    Gales, Mark J. F.
    Cipolla, Roberto
    14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2666 - 2668