Learning-Based Image Restoration for Compressed Image through Neighboring Embedding

Authors:
Lin Ma;Feng Wu;Debin Zhao;Wen Gao;Siwei Ma
Affiliations:
School of Computer Scinence and Technology, Harbin Institure of Technology, Harbin, P. R. China 150001;Microsoft Research Asia, Beijing, P. R. China 100080;School of Computer Scinence and Technology, Harbin Institure of Technology, Harbin, P. R. China 150001;School of Computer Scinence and Technology, Harbin Institure of Technology, Harbin, P. R. China 150001 and School of Electronics Engineering and Computer Science, Peking University, Beijing, P. R. ...;School of Electronics Engineering and Computer Science, Peking University, Beijing, P. R. China 100080
Venue:
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2008

Citing 10
Cited 0

Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
JPEG Still Image Data Compression Standard

JPEG Still Image Data Compression Standard
Vision: A Computational Investigation into the Human Representation and Processing of Visual Information

Vision: A Computational Investigation into the Human Representation and Processing of Visual Information
Resolution enhancement by prediction of the high-frequency image based on the Laplacian pyramid

EURASIP Journal on Applied Signal Processing
A vector quantizer for image restoration

IEEE Transactions on Image Processing
Postprocessing for very low bit-rate video compression

IEEE Transactions on Image Processing
Image enhancement by nonlinear extrapolation in frequency space

IEEE Transactions on Image Processing
A VQ-based blind image restoration algorithm

IEEE Transactions on Image Processing
A deblocking method for BDCT compressed images based on adaptive projections

IEEE Transactions on Circuits and Systems for Video Technology
Fast Edge-Preserved Postprocessing for Compressed Images

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel learning-based image restoration scheme for compressed images by suppressing compression artifacts and recovering high frequency components with the priors learned from a training set of natural images. Specifically, Deblocking is performed to alleviate the blocking artifacts. Moreover, consistency of the primitives is enhanced by estimating the high frequency components, which are simply truncated during quantization. Furthermore, with the assumption that small image patches in the enhanced and real high frequency images form manifolds with similar local geometry in the corresponding image feature spaces, a neighboring embedding-based mapping strategy is utilized to reconstruct the target high frequency components. And experimental results have demonstrated that the proposed scheme can reproduce higher-quality images in terms of visual quality and PSNR, especially the regions relating to the contours.