Highly Corrupted Image Inpainting Through Hypoelliptic Diffusion

被引：8

作者：

Boscain, Ugo V. ^{[1
,2
]}

Chertovskih, Roman ^{[3
,4
]}

Gauthier, Jean-Paul ^{[5
]}

Prandi, Dario ^{[6
]}

Remizov, Alexey O. ^{[7
]}

机构：

[1] UPMC Univ Paris 06, CNRS, Lab Jacques Louis Lions, F-75005 Paris, France

[2] INRIA, INRIA Team CAGE, Paris, France

[3] Univ Porto, Res Ctr Syst & Technol, Fac Engn, Rua Dr Roberto Frias S-N, P-4200465 Porto, Portugal

[4] Samara Natl Res Univ, 34 Moskovskoye Ave, Samara 443086, Russia

[5] Univ Toulon USTV, LSIS, UMR CNRS 7296, F-83957 La Garde, France

[6] Cent Supelec, CNRS, L2S, 3 Rue Joliot Curie, F-91192 Gif Sur Yvette, France

[7] CMAP Ecole Polytech, CNRS, F-91128 Palaiseau, France

来源：

JOURNAL OF MATHEMATICAL IMAGING AND VISION | 2018年 / 60卷 / 08期

基金：

欧洲研究理事会;

关键词：

Image reconstruction; Inpainting; Sub-Riemannian hypoelliptic diffusion; INVARIANT PARABOLIC EVOLUTIONS; INVERTIBLE ORIENTATION SCORES; CONTOUR ENHANCEMENT; RECONSTRUCTION; FRAMEWORK; EQUATIONS; FIELDS; SE(2);

D O I：

10.1007/s10851-018-0810-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present a new biomimetic image inpainting algorithm, the Averaging and Hypoelliptic Evolution (AHE) algorithm, inspired by the one presented in Boscain et al. (SIAM J. Imaging Sci. 7(2):669-695, 2014) and based upon a semi-discrete variation of the Citti-Petitot-Sarti model of the primary visual cortex V1. The AHE algorithm is based on a suitable combination of sub-Riemannian hypoelliptic diffusion and ad hoc local averaging techniques. In particular, we focus on highly corrupted images (i.e., where more than the 80% of the image is missing), for which we obtain high-quality reconstructions.

引用

页码：1231 / 1245

页数：15

共 50 条

[11] Image Inpainting Based on Improved Tensor Diffusion Model
Cui Xuehong
Pan Zhenkuan
Wei Weibo
ICCSE 2008: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE & EDUCATION: ADVANCED COMPUTER TECHNOLOGY, NEW EDUCATION, 2008, : 833 - 837
[12] IMAGE INPAINTING THROUGH NEURAL NETWORKS HALLUCINATIONS
Fawzi, Alhussein
Samulowitz, Horst
Turaga, Deepak
Frossard, Pascal
2016 IEEE 12TH IMAGE, VIDEO, AND MULTIDIMENSIONAL SIGNAL PROCESSING WORKSHOP (IVMSP), 2016,
[13] Image Inpainting Based on Fractional-Order Nonlinear Diffusion for Image Reconstruction
Sridevi, G.
Kumar, S. Srinivas
CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2019, 38 (08) : 3802 - 3817
[14] Image Inpainting Based on Fractional-Order Nonlinear Diffusion for Image Reconstruction
G. Sridevi
S. Srinivas Kumar
Circuits, Systems, and Signal Processing, 2019, 38 : 3802 - 3817
[15] Learning Sparse Masks for Diffusion-Based Image Inpainting
Alt, Tobias
Peter, Pascal
Weickert, Joachim
PATTERN RECOGNITION AND IMAGE ANALYSIS (IBPRIA 2022), 2022, 13256 : 528 - 539
[16] Nonlocal Curvature-Driven Diffusion Model for Image Inpainting
Li, Li
Yu, Han
FIFTH INTERNATIONAL CONFERENCE ON INFORMATION ASSURANCE AND SECURITY, VOL 2, PROCEEDINGS, 2009, : 513 - 516
[17] The highly lose image inpainting method based on human vision
Hsieh, Ching-Tang
Lai, Eugene
Yang, Ping-Da
Chen, Yen-Liang
ICICIC 2006: FIRST INTERNATIONAL CONFERENCE ON INNOVATIVE COMPUTING, INFORMATION AND CONTROL, VOL 2, PROCEEDINGS, 2006, : 697 - +
[18] Anti-forensics of diffusion-based image inpainting
Dou, Liyun
Qian, Zhenxing
Qin, Chuan
Feng, Guorui
Zhang, Xinpeng
JOURNAL OF ELECTRONIC IMAGING, 2020, 29 (04)
[19] Research of Diffusion Coefficient in The Total Variation Image Inpainting Model
He Jing
Zhao Feng-qun
Zhou Qian
Zhang Pei-ru
PROCEEDINGS OF FIRST INTERNATIONAL CONFERENCE OF MODELLING AND SIMULATION, VOL III: MODELLING AND SIMULATION IN ELECTRONICS, COMPUTING, AND BIO-MEDICINE, 2008, : 382 - 386
[20] Restoration of Highly Impulses Corrupted Color Image by Local Entropy Measure
You, Bing
2014 INTERNATIONAL SYMPOSIUM ON COMPUTER, CONSUMER AND CONTROL (IS3C 2014), 2014, : 769 - 772

← 1 2 3 4 5 →