Name
Abstract | ||
|---|---|---|
Recently, most deep convolutional neural networks used for image super-resolution have achieved impressive performance on ideal datasets. However, these methods always fail in real-world super-resolution, and the results are blurred and structurally deformed. In this paper, a multiscale generative adversarial network (MGAN) is proposed to alleviate these issues. The model's multiscale loss function can effectively reduce the solution space and obtain the best features to reconstruct the image. The degraded framework based on kernel estimation and noise injection is mainly applied to obtain LR images that share the same domain with real-world pictures. Moreover, the gradient branch is presented to provide other structural priors for SR processing. Simultaneously, to obtain better visual effects, LPIPS is used for perceptual losses instead of Visual Geometry Group (VGG). The competitive results show that our MGAN model outperforms the state-of-the-art methods, resulting in lower noise and better visual quality, and reflects the superiority in image structure restoration. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1002/cpe.6430 | CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE |
Keywords | DocType | Volume |
gradient branch, loss function, real-world super-resolution, visual quality | Journal | 33 |
Issue | ISSN | Citations |
21 | 1532-0626 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ying Sun | 1 | 291 | 40.03 |
| Zhiwen Yang | 2 | 0 | 0.34 |
| Bo Tao | 3 | 37 | 17.60 |
| Guozhang Jiang | 4 | 0 | 1.35 |
| Zhiqiang Hao | 5 | 0 | 0.34 |
| Baojia Chen | 6 | 0 | 2.03 |