Abstract | ||
---|---|---|
The Block-wise Discrete Cosine Transform (B-DCT) based compression technique has been widely used in image and video coding standards. However, at high compression ratios, the coded images inevitably contain annoying blocking artifacts. In this paper, the author proposes a novel variational model for blocking artifacts suppression, which combines a discriminatively trained Fields of Experts (FoE) image prior model and the indicator function of the quantization constraint set (QCS). The FoE prior model is a filter-based higher-order Markov Random Fields (MRF) model, and it has proven to be effective for many image restoration problems. The resulting variational model leads to a generally difficult non-convex optimization problem, which can be efficiently solved by a recently proposed non-convex optimization algorithm. Numerical experiments show that the proposed deblocking approach leads to visually strongly comparable performance to state-of-the-art deblocking methods across a range of compression levels. Furthermore, our method can achieve higher PSNR-B results, which is a block-sensitive index, specialized for deblocked image evaluation and correlates well with subjective quality. Besides, the proposed model comes along with the additional advantage of high efficiency. HighlightsA variational model combining a Fields of Experts prior and the quantization constraint set is propose for JPEG deblocking.The exploited QCS is usually lacking in traditional JPEG deblocking approaches.The resulting non-convex optimization problem is efficiently solved by a forward-backward splitting algorithm.Our model leads to higher PSNR-B results and visually comparable performance to state-of-the-art deblocking methods. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1016/j.image.2016.12.006 | Sig. Proc.: Image Comm. |
Keywords | Field | DocType |
JPEG deblocking,Fields of Experts,Non-convex optimization,MRFs | Computer vision,Compression artifact,Computer science,Discrete cosine transform,Markov chain,JPEG,Artificial intelligence,Image restoration,Quantization (signal processing),Optimization problem,Deblocking filter | Journal |
Volume | Issue | ISSN |
52 | C | 0923-5965 |
Citations | PageRank | References |
1 | 0.36 | 16 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yunjin Chen | 1 | 407 | 14.89 |