Joint Patch-Group Based Sparse Representation for Image Inpainting

Zhiyuan Zha, Xin Yuan, Bihan Wen, Jiantao Zhou, Ce Zhu
Proceedings of The 10th Asian Conference on Machine Learning, PMLR 95:145-160, 2018.

Abstract

Sparse representation has achieved great successes in various machine learning and image processing tasks. For image processing, typical patch-based sparse representation (PSR) models usually tend to generate undesirable visual artifacts, while group-based sparse representation (GSR) models produce over-smooth phenomena. In this paper, we propose a new sparse representation model, termed joint patch-group based sparse representation (JPG-SR). Compared with existing sparse representation models, the proposed JPG-SR provides a powerful mechanism to integrate the local sparsity and nonlocal self-similarity of images. We then apply the proposed JPG-SR model to a low-level vision problem, namely, image inpainting. To make the proposed scheme tractable and robust, an iterative algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed JPG-SR model. Experimental results demonstrate that the proposed model is efficient and outperforms several state-of-the-art methods in both objective and perceptual quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v95-zha18a, title = {Joint Patch-Group Based Sparse Representation for Image Inpainting}, author = {Zha, Zhiyuan and Yuan, Xin and Wen, Bihan and Zhou, Jiantao and Zhu, Ce}, booktitle = {Proceedings of The 10th Asian Conference on Machine Learning}, pages = {145--160}, year = {2018}, editor = {Zhu, Jun and Takeuchi, Ichiro}, volume = {95}, series = {Proceedings of Machine Learning Research}, month = {14--16 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v95/zha18a/zha18a.pdf}, url = {https://proceedings.mlr.press/v95/zha18a.html}, abstract = {Sparse representation has achieved great successes in various machine learning and image processing tasks. For image processing, typical patch-based sparse representation (PSR) models usually tend to generate undesirable visual artifacts, while group-based sparse representation (GSR) models produce over-smooth phenomena. In this paper, we propose a new sparse representation model, termed joint patch-group based sparse representation (JPG-SR). Compared with existing sparse representation models, the proposed JPG-SR provides a powerful mechanism to integrate the local sparsity and nonlocal self-similarity of images. We then apply the proposed JPG-SR model to a low-level vision problem, namely, image inpainting. To make the proposed scheme tractable and robust, an iterative algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed JPG-SR model. Experimental results demonstrate that the proposed model is efficient and outperforms several state-of-the-art methods in both objective and perceptual quality.} }
Endnote
%0 Conference Paper %T Joint Patch-Group Based Sparse Representation for Image Inpainting %A Zhiyuan Zha %A Xin Yuan %A Bihan Wen %A Jiantao Zhou %A Ce Zhu %B Proceedings of The 10th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jun Zhu %E Ichiro Takeuchi %F pmlr-v95-zha18a %I PMLR %P 145--160 %U https://proceedings.mlr.press/v95/zha18a.html %V 95 %X Sparse representation has achieved great successes in various machine learning and image processing tasks. For image processing, typical patch-based sparse representation (PSR) models usually tend to generate undesirable visual artifacts, while group-based sparse representation (GSR) models produce over-smooth phenomena. In this paper, we propose a new sparse representation model, termed joint patch-group based sparse representation (JPG-SR). Compared with existing sparse representation models, the proposed JPG-SR provides a powerful mechanism to integrate the local sparsity and nonlocal self-similarity of images. We then apply the proposed JPG-SR model to a low-level vision problem, namely, image inpainting. To make the proposed scheme tractable and robust, an iterative algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed JPG-SR model. Experimental results demonstrate that the proposed model is efficient and outperforms several state-of-the-art methods in both objective and perceptual quality.
APA
Zha, Z., Yuan, X., Wen, B., Zhou, J. & Zhu, C.. (2018). Joint Patch-Group Based Sparse Representation for Image Inpainting. Proceedings of The 10th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 95:145-160 Available from https://proceedings.mlr.press/v95/zha18a.html.

Related Material