Learning-Based Image Restoration for Compressed Image through Neighboring Embedding

Ma, Lin; Wu, Feng; Zhao, Debin; Gao, Wen; Ma, Siwei

doi:10.1007/978-3-540-89796-5_29

Cited by 10 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, postprocessing techniques based on perceptual cues have been proposed (Chetouani et al 2009;Liu et al 2010), which can efficiently reconstruct the distorted image with high perceptual quality. In addition, learning-based image restoration scheme for compressed images was proposed in Ma et al (2008), in which the high-frequency components with the priors are learned from a training set of natural images. 220 12 Hot Research Topics in Video Coding and Systems…”

Section: Preprocessing and Postprocessingmentioning

confidence: 99%

Advanced Video Coding Systems

Gao

2014

Self Cite

View full text Add to dashboard Cite

Section: Preprocessing and Postprocessingmentioning

confidence: 99%

Advanced Video Coding Systems

Gao

2014

Self Cite

View full text Add to dashboard Cite

“…Some research devote to the post processing or image iteratively recovery methods based on the theory of projections onto convex sets (POCS) [6]. Recently, learning-based image restoration [7]- [9] have emerged to deal with the artifices in the compressed images and videos.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, learning-based image restoration [7] has been proposed to rebuild a high-quality image from a codebook which contains the HF components for the low quality image. Because a patch of degraded images can be mapped to more than one high-frequency patches, the learning-based image restoration is an ill-posed problem in essence.…”

Section: Introductionmentioning

confidence: 99%

Compressed Vision Information Restoration Based on Cloud Prior and Local Prior

Jiang

et al. 2014

IEEE Access

Self Cite

View full text Add to dashboard Cite

In wireless communication, compressed vision information may suffer from kinds of degradation, which dramatically influences the final visual quality. In this paper, a compressed vision information restoration method is proposed based on two explored vision priors: 1) the cloud prior and 2) the local prior. The cloud prior can be obtained from the nature images set in the cloud, and fields of experts is used to formulate the statistical character of the nature image contents as a high order Markov random field. The local prior is achieved from the degraded image itself, and K-SVD is adopted to model the sparse and redundant representation characters of nature images. These priors are effectively comprised in the proposed vision information restoration method. The relation between the quantization parameter and the optimal configuration of the prior models is further analyzed. In addition, an enhanced quantization constrained projection algorithm is proposed to refine the high frequency components. We extend this paper to compressed video restoration for H.264/AVC and the experiment results demonstrate that the proposed scheme can reproduce higher quality images compared with conventional H.264/AVC. INDEX TERMS Nature image prior, high-quality image restoration, fields of experts, K-SVD.

show abstract

“…At present, a lot of researchers consider the learning-based algorithm as a very promising approach and think it is a hot spot in the field of super-resolution [1]. The algorithm of learningbased in super-resolution is through learning to get the relation between high-resolution and lowresolution to guide the high-resolution image reconstruction [2]- [5]. The learning-based algorithm makes full use of the prior knowledge of image itself and is applicable to the face and text image restoration [6,7].…”

Section: Introductionmentioning

confidence: 99%

Image Restoration Through Dictionary Learning and Sparse Representation

Wang¹

2013

J. Inf. Comput. Sci.

View full text Add to dashboard Cite

Based on the content dual-dictionary learning and sparse representation, we put forward a novel method of image restoration. This method can improve the adaptive ability of the image. To restore the image, the dual-dictionary is trained with sparse representation. Comparing with the traditional dictionary learning algorithm, the method in this paper can capture more high-frequency information and enhance the image quality further in image reconstruction. The experimental results show that the proposed method is useful for image restoration and much better than other methods.

show abstract

Learning-Based Image Restoration for Compressed Image through Neighboring Embedding

Cited by 10 publications

References 11 publications

Advanced Video Coding Systems

Advanced Video Coding Systems

Compressed Vision Information Restoration Based on Cloud Prior and Local Prior

Image Restoration Through Dictionary Learning and Sparse Representation

Contact Info

Product

Resources

About