High efficiency depth image-based rendering with simplified inpainting-based hole filling

被引:5
|
作者
Kuo, Pin-Chen [1 ]
Lin, Jhih-Ming [1 ]
Liu, Bin-Da [1 ]
Yang, Jar-Ferr [1 ]
机构
[1] Natl Cheng Kung Univ, Dept Elect Engn, Adv Optoelect Technol Ctr, One Univ Rd, Tainan 70101, Taiwan
关键词
View synthesis; Hole filling; Crack filling; Inpainting; Graphics processing unit (GPU); Depth-image-based rendering (DIBR); REPRESENTATION; ALGORITHM;
D O I
10.1007/s11045-015-0378-8
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Hole and crack filling is the most important issue in depth-image-based rendering (DIBR) algorithms for generating virtual view images when only one view image and one depth map are available. This paper proposes a priority patch inpainting algorithm for hole filling in DIBR algorithms by generating multiple virtual views. A texture-based interpolation method is applied for crack filling. Then, an inpainting-based algorithm is applied patch by patch for hole filling. A prioritized method for selecting the critical patch is also proposed to reduce computation time. Finally, the proposed method is realized on the compute unified device architecture parallel computing platform which runs on a graphics processing unit. Simulation results show that the proposed algorithm is 51-fold faster for virtual view synthesis and achieves better virtual view quality compared to the traditional DIBR algorithm which contains depth preprocessing, warping, and hole filling.
引用
收藏
页码:623 / 645
页数:23
相关论文
共 50 条
  • [1] High efficiency depth image-based rendering with simplified inpainting-based hole filling
    Pin-Chen Kuo
    Jhih-Ming Lin
    Bin-Da Liu
    Jar-Ferr Yang
    Multidimensional Systems and Signal Processing, 2016, 27 : 623 - 645
  • [2] SPRITE GENERATION FOR HOLE FILLING IN DEPTH IMAGE-BASED RENDERING
    Lin, Guo-Shiang
    Hsieh, Chia-Yung
    Lie, Wen-Nung
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 5402 - 5406
  • [3] Depth Similarity Enhanced Image Summarization Algorithm for Hole-Filling in Depth Image-Based Rendering
    Song Lin
    Hu Ruimin
    Zhong Rui
    CHINA COMMUNICATIONS, 2014, 11 (11) : 60 - 68
  • [4] AN EFFICIENT HOLE FILLING FOR DEPTH IMAGE BASED RENDERING
    Cigla, Cevahir
    Alatan, A. Aydm
    ELECTRONIC PROCEEDINGS OF THE 2013 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (ICMEW), 2013,
  • [5] Key-Frame-Based Background Sprite Generation for Hole Filling in Depth Image-Based Rendering
    Lie, Wen-Nung
    Hsieh, Chia-Yung
    Lin, Guo-Shiang
    IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (05) : 1075 - 1087
  • [6] An enhanced non local mean method for hole filling in the depth image-based rendering system
    Zhang, Zihao
    Wang, Yuanqing
    Zhan, Lingli
    ELEVENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2019), 2019, 11179
  • [7] Hole-filling approach based on convolutional neural network for depth image-based rendering view synthesis
    Cai, Chengtao
    Fan, Bing
    Meng, Haiyang
    Zhu, Qidan
    JOURNAL OF ELECTRONIC IMAGING, 2020, 29 (01)
  • [8] A Hole Filling Algorithm for Depth Image Based Rendering Based on Gradient Information
    Wang, Dan
    Zhao, Yan
    Wang, Jing-yuan
    Wang, Zheng
    2013 NINTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION (ICNC), 2013, : 1209 - 1213
  • [9] Hole Filling Method for Depth Image Based Rendering Based on Boundary Decision
    Cho, Jea-Hyung
    Song, Wonseok
    Choi, Hyuk
    Kim, Taejeong
    IEEE SIGNAL PROCESSING LETTERS, 2017, 24 (03) : 329 - 333
  • [10] Faithful Disocclusion Filling in Depth Image Based Rendering Using Superpixel-Based Inpainting
    Schmeing, Michael
    Jiang, Xiaoyi
    IEEE TRANSACTIONS ON MULTIMEDIA, 2015, 17 (12) : 2160 - 2173