Journal ArticleDOI
Low-Rank Decomposition-Based Restoration of Compressed Images via Adaptive Noise Estimation
Reads0
Chats0
TLDR
This paper proposes a unified framework of content-adaptive estimation and reduction for compression noise via low-rank decomposition of similar image patches, which improves the quality of compressed images obviously for post-processing, but are also helpful for computer vision tasks as a pre-processing method.Abstract:
Images coded at low bit rates in real-world applications usually suffer from significant compression noise, which significantly degrades the visual quality. Traditional denoising methods are not suitable for the content-dependent compression noise, which usually assume that noise is independent and with identical distribution. In this paper, we propose a unified framework of content-adaptive estimation and reduction for compression noise via low-rank decomposition of similar image patches. We first formulate the framework of compression noise reduction based upon low-rank decomposition. Compression noises are removed by soft thresholding the singular values in singular value decomposition of every group of similar image patches. For each group of similar patches, the thresholds are adaptively determined according to compression noise levels and singular values. We analyze the relationship of image statistical characteristics in spatial and transform domains, and estimate compression noise level for every group of similar patches from statistics in both domains jointly with quantization steps. Finally, quantization constraint is applied to estimated images to avoid over-smoothing. Extensive experimental results show that the proposed method not only improves the quality of compressed images obviously for post-processing, but are also helpful for computer vision tasks as a pre-processing method.read more
Citations
More filters
Journal ArticleDOI
Content-Aware Convolutional Neural Network for In-Loop Filtering in High Efficiency Video Coding
TL;DR: This paper quantitatively analyzes the structure of the proposed CNN model from multiple dimensions to make the model interpretable and optimal for CNN-based loop filtering for high-efficiency video coding (HEVC).
Journal ArticleDOI
Random Walk Graph Laplacian-Based Smoothness Prior for Soft Decoding of JPEG Images
TL;DR: Li et al. as discussed by the authors proposed a graph-signal smoothness prior (LERaG) based on the left eigenvectors of the random walk graph Laplacian matrix, which has desirable image filtering properties with low computation overhead.
Proceedings ArticleDOI
JPEG Artifacts Reduction via Deep Convolutional Sparse Coding
TL;DR: This work designs a deep convolutional sparse coding network architecture in the framework of classic learned iterative shrinkage-threshold algorithm that generates comparable or better de-blocking results when compared with state-of-the-art methods.
Journal ArticleDOI
High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity
TL;DR: This paper presents a novel image restoration method that combines nonlocal self-similarity and global structure sparsity in a single efficient model and shows it to outperform state-of-the-art approaches for these tasks, for various types and levels of image corruption.
Proceedings ArticleDOI
DPW-SDNet: Dual Pixel-Wavelet Domain Deep CNNs for Soft Decoding of JPEG-Compressed Images
TL;DR: Wang et al. as discussed by the authors developed a dual pixel-wavelet domain deep CNNs-based soft decoding network for JPEG-compressed images, namely DPW-SDNet, which takes the four downsampled versions of the compressed image to form a 4-channel input and outputs a pixel domain prediction.
References
More filters
Journal ArticleDOI
Image quality assessment: from error visibility to structural similarity
TL;DR: In this article, a structural similarity index is proposed for image quality assessment based on the degradation of structural information, which can be applied to both subjective ratings and objective methods on a database of images compressed with JPEG and JPEG2000.
Journal ArticleDOI
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Journal ArticleDOI
De-noising by soft-thresholding
TL;DR: The authors prove two results about this type of estimator that are unprecedented in several ways: with high probability f/spl circ/*/sub n/ is at least as smooth as f, in any of a wide variety of smoothness measures.
Journal ArticleDOI
Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering
TL;DR: An algorithm based on an enhanced sparse representation in transform domain based on a specially developed collaborative Wiener filtering achieves state-of-the-art denoising performance in terms of both peak signal-to-noise ratio and subjective visual quality.
Proceedings ArticleDOI
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
TL;DR: In this paper, the authors present a database containing ground truth segmentations produced by humans for images of a wide variety of natural scenes, and define an error measure which quantifies the consistency between segmentations of differing granularities.