Abstract | ||
---|---|---|
A highly compressed image is usually not only of low resolution, but also suffers from compression artifacts (blocking artifact is treated as an example in this paper). Directly performing image super-resolution (SR) to a highly compressed image would also simultaneously magnify the blocking artifacts, resulting in an unpleasing visual experience. In this paper, we propose a novel learning-based framework to achieve joint single-image SR and deblocking for a highly-compressed image. We argue that individually performing deblocking and SR (i.e., deblocking followed by SR, or SR followed by deblocking) on a highly compressed image usually cannot achieve a satisfactory visual quality. In our method, we propose to learn image sparse representations for modeling the relationship between low- and high-resolution image patches in terms of the learned dictionaries for image patches with and without blocking artifacts, respectively . As a result, image SR and deblocking can be simultaneously achieved via sparse representation and morphological component analysis (MCA)-based image decomposition. Experimental results demonstrate the efficacy of the proposed algorithm. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/TMM.2015.2434216 | IEEE Trans. Multimedia |
Keywords | Field | DocType |
Image coding,Dictionaries,Hafnium,Training,Joints,Noise reduction,Image resolution | Computer vision,Pattern recognition,Feature detection (computer vision),Image texture,Computer science,Binary image,Image quality,Image processing,Artificial intelligence,Image restoration,Deblocking filter,Image compression | Journal |
Volume | Issue | ISSN |
17 | 7 | 1520-9210 |
Citations | PageRank | References |
19 | 0.65 | 32 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Li-Wei Kang | 1 | 340 | 19.30 |
Chih-Chung Hsu | 2 | 125 | 11.31 |
Boqi Zhuang | 3 | 19 | 0.65 |
Chia-Wen Lin | 4 | 1639 | 120.23 |
Chia-Hung Yeh | 5 | 367 | 42.15 |