Image inpainting via sparse representation

Authors:
Bin Shen; Wei Hu;Yimin Zhang;Yu-Jin Zhang
Affiliations:
Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China;Intel China Research Center, Beijing, China;Intel China Research Center, Beijing, China;Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
Venue:
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Year:
2009

Citing 0
Cited 6

Foreground segmentation via sparse representation

SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Image inpainting by patch propagation using patch sparsity

IEEE Transactions on Image Processing
Missing texture reconstruction method based on perceptually optimized algorithm

EURASIP Journal on Advances in Signal Processing
Sparse Doppler-only snapshot imaging for space debris

Signal Processing
Learning Big (Image) Data via Coresets for Dictionaries

Journal of Mathematical Imaging and Vision
A color-gradient patch sparsity based image inpainting algorithm with structure coherence and neighborhood consistency

Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel patch-wise image inpainting algorithm using the image signal sparse representation over a redundant dictionary, which merits in both capabilities to deal with large holes and to preserve image details while taking less risk. Different from all existing works, we consider the problem of image inpainting from the view point of sequential incomplete signal recovery under the assumption that the every image patch admits a sparse representation over a redundant dictionary. To ensure the visually plausibility and consistency constraints between the filled hole and the surroundings, we propose to construct a redundant signal dictionary by directly sampling from the intact source region of current image. Then we sequentially compute the sparse representation for each incomplete patch at the boundary of the hole and recover it until the whole hole is filled. Experimental results show that this approach can efficiently fill in the hole with visually plausible information, and take less risk to introduce unwanted objects or artifacts.