Frequency-Based Environment Matting of Transparent Objects Using Kaczmarz Method

被引:0
|
作者
Chang, I-Cheng [1 ]
Yang, Tian-Lin [2 ]
Huang, Chung-Lin [2 ]
机构
[1] Natl Dong Hwa Univ, Dept Comp Sci & Informat Engn, Hualien 974, Taiwan
[2] Natl Tsing Hua Univ, Dept Elect Engn, Hsinchu 300, Taiwan
关键词
environment matting; transparent object; Kaczmarz method; weight matrix; iterative projection;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Digital compositing is an important topic in the field of computer graphics and image processing. Many works have sought a good method to prevent composited images from being distinguishable from real images. The paper proposes a new environment matting algorithm to model the appearance of transparent object under different backgrounds. In the proposed approach, the frequency-domain analysis is adopted to compute the relationship between the area of foreground object and background image. Furthermore, the Kaczmarz method is applied to compute the caustics from refraction by transparent objects. The experimental results show that the algorithm effectively improves the quality of composited image and has a high PSNR. In addition, the composited results are also demonstrated by a video sequence involved of the motion, rotation and scaling of the transparent object.
引用
收藏
页码:1413 / 1428
页数:16
相关论文
共 50 条
  • [1] Frequency-based environment matting
    Zhu, JY
    Yang, YH
    12TH PACIFIC CONFERENCE ON COMPUTER GRAPHICS AND APPLICATIONS, PROCEEDINGS, 2004, : 402 - 410
  • [2] Environment matting of transparent objects based on frequency-domain analysis
    Chang, IC
    Yang, YL
    Huang, CL
    ADVANCES IN MULTIMEDIA INFORMATION PROCESSING - PCM 2005, PT 1, 2005, 3767 : 37 - 48
  • [3] Frequency-based Environment Matting by Compressive Sensing
    Qian, Yiming
    Gong, Minglun
    Yang, Yee-Hong
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 3532 - 3540
  • [4] Frequency-Based 3D Reconstruction of Transparent and Specular Objects
    Liu, Ding
    Chen, Xida
    Yang, Yee-Hong
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 660 - 667
  • [5] NEMTO: Neural Environment Matting for Novel View and Relighting Synthesis of Transparent Objects
    Wang, Dongqing
    Zhang, Tong
    Susstrunk, Sabine
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 317 - 327
  • [6] VECTOR FIELD FITTING FOR REAL-TIME ENVIRONMENT MATTING OF TRANSPARENT OBJECTS
    Duan, Qi
    Cai, Jianfei
    Zheng, Jianmin
    2009 16TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-6, 2009, : 3229 - 3232
  • [7] Frequency-based categorization of complex visual objects
    Haushofer, J.
    Baker, C. I.
    Kanwisher, N.
    PERCEPTION, 2007, 36 : 100 - 100
  • [8] Learning Super-Resolution of Environment Matting of Transparent Objects From a Single Image
    Hang, Zicun
    Yang, Yee-Hong
    IEEE ACCESS, 2022, 10 : 3548 - 3558
  • [9] Learning Super-Resolution of Environment Matting of Transparent Objects From a Single Image
    Hang, Zicun
    Yang, Yee-Hong
    IEEE Access, 2022, 10 : 3548 - 3558
  • [10] Instruction Frequency-based Malware Classification Method
    Han, Kyoung Soo
    Kim, Sung-Ryul
    Im, Eul Gyu
    INFORMATION-AN INTERNATIONAL INTERDISCIPLINARY JOURNAL, 2012, 15 (07): : 2973 - 2983