A joint motion-image inpainting method for error concealment in video coding

被引:6
作者
Chen, L. Y. [1 ]
Chan, S. C. [1 ]
Shum, H. Y. [2 ]
机构
[1] Chinese Univ Hong Kong, Dept Elect & Elect Engn, Sha Tin 100083, Peoples R China
[2] Microsoft Res Asia, Beijing, Peoples R China
来源
2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS | 2006年
关键词
error concealment; markov random field; motion inpainting; image inpainting;
D O I
10.1109/ICIP.2006.312808
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we propose a new method for spatial-temporal error concealment in video coding using joint motion-image inpainting. The proposed method combines motion inpainting and adaptive Markov random field (MRF) based diffusion as robust motion inpainting. Image inpainting is employed to refine the result. With robust motion inpainting, effective compromise between temporal and spatial method is achieved for each point in the missing marcroblock (MB), which provides satisfactory visual quality of the restored frame with complex motion in video.
引用
收藏
页码:2241 / +
页数:2
相关论文
共 14 条
[1]   Error resilience in the MPEG-2 video coding standard for cell based networks - A review [J].
Arnold, JF ;
Frater, MR ;
Zhang, J .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 1999, 14 (6-8) :607-633
[2]  
BELFIORE S, 2003, ICASSP 2003 IEEE INT
[3]  
BELFIORE S, 2002, TYRRH INT WORKSH DIG
[4]  
Bouguet J.Y., 2000, Pyramidal implementation of the lucas kanade feature tracker description of the algorithm
[5]  
CRIMINISI A, 2003, IEEE C COMP VIS PATT, V2, P707
[6]   Image analogies [J].
Hertzmann, A ;
Jacobs, CE ;
Oliver, N ;
Curless, B ;
Salesin, DH .
SIGGRAPH 2001 CONFERENCE PROCEEDINGS, 2001, :327-340
[7]  
JUNG KH, 1994, P SOC PHOTO-OPT INS, V2308, P1466, DOI 10.1117/12.185905
[8]   Comparison of error concealment techniques for an MPEG-2 video decoder in terrestrial TV-broadcasting [J].
Kaiser, S ;
Fazel, K .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 1999, 14 (6-8) :655-676
[9]  
LAM WM, 1993, P ICASSP, V5, P417
[10]  
Matsushita Y, 2005, PROC CVPR IEEE, P50