Depth Map Upsampling and Refinement for FTV Systems

被引:2
|
作者
Dziembowski, Adrian [1 ]
Grzelka, Adam [1 ]
Mieloch, Dawid [1 ]
Stankiewicz, Olgierd [1 ]
Domanski, Marek [1 ]
机构
[1] Poznan Univ Tech, Chair Multimedia Telecommun & Microelect, Poznan, Poland
关键词
depth map upsampling; depth map refinement; segmentation; free-viewpoint television; virtual navigation;
D O I
10.1109/ICSES.2016.7593827
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In free-viewpoint television, high-quality depth maps are substantial for a virtual view synthesis for free navigation purposes. In this paper, we propose a new method of depth map quality improvement and resolution increase. Our method is intended for low resolution depth maps acquired through estimation using multiview video. The proposed depth map quality improvement is based on segmentation of an acquired high-resolution image. In the estimated depth map, searching for outliers is performed in the neighborhood created from similar segments in the acquired view. Experimental results show high effectiveness of the presented method of depth maps refinement, especially for object edges.
引用
收藏
页码:89 / 92
页数:4
相关论文
共 50 条
  • [41] Depth Map Super-resolution Via Iterative Joint-Trilateral-Upsampling
    Li, Yangguang
    Zhang, Lei
    Zhang, Yongbing
    Xuan, Huiming
    Dai, Qionghai
    2014 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING CONFERENCE, 2014, : 386 - 389
  • [42] Precise depth map upsampling and enhancement based on edge-preserving fusion filters
    Chang, Ting-An
    Yang, Jar-Ferr
    IET COMPUTER VISION, 2018, 12 (05) : 651 - 658
  • [43] Integrated cosparse analysis model with explicit edge inconsistency measurement for guided depth map upsampling
    Zuo, Yifan
    Wu, Qiang
    An, Ping
    Shang, Xiwu
    JOURNAL OF ELECTRONIC IMAGING, 2018, 27 (04)
  • [44] Deep Weighted Guided Upsampling Network for Depth of Field Image Upsampling
    Zeng, Lanling
    Wu, Lianxiong
    Yang, Yang
    Shen, Xiangjun
    Zhan, Yongzhao
    PROCEEDINGS OF THE 4TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA IN ASIA, MMASIA 2022, 2022,
  • [45] Scene flow estimation by depth map upsampling and layer assignment for camera-LiDAR system
    Zou, Cheng
    He, Bingwei
    Zhu, Mingzhu
    Zhang, Liwei
    Zhang, Jianwei
    JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2019, 64
  • [46] Depth map super-resolution based on edge-guided joint trilateral upsampling
    Shuyuan Yang
    Ning Cao
    Bin Guo
    Gang Li
    The Visual Computer, 2022, 38 : 883 - 895
  • [47] DDRNet: Depth Map Denoising and Refinement for Consumer Depth Cameras Using Cascaded CNNs
    Yan, Shi
    Wu, Chenglei
    Wang, Lizhen
    Xu, Feng
    An, Liang
    Guo, Kaiwen
    Liu, Yebin
    COMPUTER VISION - ECCV 2018, PT X, 2018, 11214 : 155 - 171
  • [48] Depth map super-resolution based on edge-guided joint trilateral upsampling
    Yang, Shuyuan
    Cao, Ning
    Guo, Bin
    Li, Gang
    VISUAL COMPUTER, 2022, 38 (03): : 883 - 895
  • [49] Edge adaptive upsampling of depth map videos for enhanced free-viewpoint video quality
    Ekmekcioglu, E.
    Mrak, M.
    Worrall, S. T.
    Kondoz, A. M.
    ELECTRONICS LETTERS, 2009, 45 (07) : 353 - U19
  • [50] Joint Object Segmentation and Depth Upsampling
    Huang, Wenqi
    Gong, Xiaojin
    Yang, Michael Ying
    IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (02) : 192 - 196