Strong-continuation, contrast-invariant inpainting with a third-order optimal PDE

被引:64
作者
Bertalmio, Marcelo [1 ]
机构
[1] Univ Pompeu Fabra, Dept Technol, Barcelona 08003, Spain
关键词
image restoration; inpainting; partial differential equations (PDEs); IMAGE; REMOVAL;
D O I
10.1109/TIP.2006.877067
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
PDE-based image inpainting has become a very active area of research after the pioneering works of Masnou and Morel, Bertalmio et al., and Ballester et al. In this paper, we take a different approach, inspired by the excellent work of Caselles et al. We view the inpainting problem as a particular case of image interpolation in which we intend to propagate level lines. Expressing this in terms of local neighborhoods and using a Taylor expansion we derive a third-order PDE that performs inpainting. This PDE is optimal in the sense that it is the most accurate third-order PDE which can ensure continuation of level lines. The continuation is strong, allowing the restoration of thin structures occluded by a wide gap. The result is also contrast invariant. This is a novel PDE, which, in both its accuracy and contrast invariance, outperforms the approaches cited above.
引用
收藏
页码:1934 / 1938
页数:5
相关论文
共 23 条
[11]   Inference of segmented color and texture description by tensor voting [J].
Jia, JY ;
Tang, CK .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2004, 26 (06) :771-786
[12]  
Kanizsa G., 1979, ORG VISION ESSAYS GE
[13]   On missing data treatment for degraded video and film archives: A survey and a new Bayesian approach [J].
Kokaram, AC .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (03) :395-413
[14]   Disocclusion: A variational approach using level lines [J].
Masnou, S .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2002, 11 (02) :68-76
[15]  
Masnou S, 1998, 1998 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING - PROCEEDINGS, VOL 3, P259, DOI 10.1109/ICIP.1998.999016
[16]  
Nitzberg M., 1993, Filtering, Segmentation and Depth
[17]   FRONTS PROPAGATING WITH CURVATURE-DEPENDENT SPEED - ALGORITHMS BASED ON HAMILTON-JACOBI FORMULATIONS [J].
OSHER, S ;
SETHIAN, JA .
JOURNAL OF COMPUTATIONAL PHYSICS, 1988, 79 (01) :12-49
[18]  
Paragios N., 2005, Mathematical Models of Computer Vision: The Handbook
[19]   SCALE-SPACE AND EDGE-DETECTION USING ANISOTROPIC DIFFUSION [J].
PERONA, P ;
MALIK, J .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1990, 12 (07) :629-639
[20]   NONLINEAR TOTAL VARIATION BASED NOISE REMOVAL ALGORITHMS [J].
RUDIN, LI ;
OSHER, S ;
FATEMI, E .
PHYSICA D, 1992, 60 (1-4) :259-268