HIERARCHICAL LEARNING OF SPARSE IMAGE REPRESENTATIONS USING STEERED MIXTURE-OF-EXPERTS

被引：0

作者：

Jongebloed, Rolf ^{[1
]}

Verhack, Ruben ^{[1
,2
]}

Lange, Lieven ^{[1
]}

Sikora, Thomas ^{[1
]}

机构：

[1] Tech Univ Berlin, Commun Syst Lab, Berlin, Germany

[2] Univ Ghent, IMEC, IDLab, Dept Elect & Informat Syst ELIS, Ghent, Belgium

来源：

2018 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA & EXPO WORKSHOPS (ICMEW 2018) | 2018年

关键词：

Steered Mixture-of-Experts; Sparse Representation; Hidden Markov Random Field; Denoising; Image Signal Processing; Inference;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Previous research showed highly efficient compression results for low bit-rates using Steered Mixture-of-Experts (SMoE), higher rates still pose a challenge due to the non-convex optimization problem that becomes more difficult when increasing the number of components. Therefore, a novel estimation method based on Hidden Markov Random Fields is introduced taking spatial dependencies of neighboring pixels into account combined with a tree-structured splitting strategy. Experimental evaluations for images show that our approach outperforms state-of-the-art techniques using only one robust parameter set. For video and light field modeling even more gain can be expected.

引用

页数：6

共 40 条

[31] Image Inpainting with Group Based Sparse Representation using Self Adaptive Dictionary Learning [J].

Rao, T. J. V. Subrahmanyeswara ;

Rao, M. Venu Gopala ;

Aswini, T. V. N. L. .

2015 INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION ENGINEERING SYSTEMS (SPACES), 2015, :301-305

[32] Hyperspectral Image Denoising Using Spectral-Spatial Transform-Based Sparse and Low-Rank Representations [J].

Zhao, Bin ;

Ulfarsson, Magnus O. ;

Sveinsson, Johannes R. ;

Chanussot, Jocelyn .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60

[33] Selective Super-Resolution via Sparse Representations of Sharp Image Patches using Multiple Dictionaries and Bicubic Interpolation [J].

Yeganli, Faezeh ;

Nazzal, Mahmoud ;

Ozkaramanli, Huseyin .

2015 23RD SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2015, :1957-1960

[34] Image Super-Resolution using DCT Interpolation and Sparse Learning-based Method [J].

Reis, Saulo R. S. ;

Bressan, Graca .

FIFTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2013), 2013, 8878

[35] A new compressive sensing based image denoising method using block-matching and sparse representations over learned dictionaries [J].

Shahdoosti, Hamid Reza ;

Hazavei, Seyede Mahya .

MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (09) :12561-12582

[36] A new compressive sensing based image denoising method using block-matching and sparse representations over learned dictionaries [J].

Hamid Reza Shahdoosti ;

Seyede Mahya Hazavei .

Multimedia Tools and Applications, 2019, 78 :12561-12582

[37] Supervised dictionary learning for blind image quality assessment using quality-constraint sparse coding [J].

Jiang, Qiuping ;

Shao, Feng ;

Jiang, Gangyi ;

Yu, Mei ;

Peng, Zongju .

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2015, 33 :123-133

[38] Reconstruction of high spectral resolution multispectral image using dictionary-based learning and sparse coding [J].

Ghosh, Dipanwita ;

Chakravortty, Somdatta .

GEOCARTO INTERNATIONAL, 2022, 37 (25) :10798-10818

[39] Iris classification based on sparse representations using on-line dictionary learning for large-scale de-duplication applications [J].

Nalla, Pattabhi Ramaiah ;

Chalavadi, Krishna Mohan .

SPRINGERPLUS, 2015, 4

[40] Medical image fusion by sparse-based modified fusion framework using block total least-square update dictionary learning algorithm [J].

Saini, Lalit Kumar ;

Mathur, Pratistha .

JOURNAL OF MEDICAL IMAGING, 2022, 9 (05)

← 1 2 3 4 →