Abstract | ||
---|---|---|
Although various single-image super-resolution algorithms have been developed to increase image resolution, they still do not provide adequate performance in the texture region due to the lack of fine textures in the processed image. In this paper, we present a novel texture enhancement strategy in order to improve the super-resolution performance in the texture region. For texture enhancement, we extract a low-resolution texture layer from an input image and generate a high-resolution texture layer by applying the proposed texture synthesis algorithm. A texture enhanced high-resolution image is then obtained by properly combining the generated high-resolution texture layer with an image obtained by using an existing single-image super-resolution algorithm. Experimental results show that the proposed texture enhancement strategy provides sharper and more natural looking textures compared with the existing super-resolution algorithms. This paper addresses a key remaining issue, texture SR, which is yet unresolved.Patch-based texture synthesis is performed by using a LR texture layer.A HR texture patch is synthesized based on both AR and reconstruction models.The proposed algorithm provides realistic SR images with sharp and fine textures. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1016/j.image.2016.04.007 | Sig. Proc.: Image Comm. |
Keywords | Field | DocType |
Texture enhancement,Single-image super-resolution,Texture synthesis | Computer vision,Texture compression,Image texture,Computer science,Artificial intelligence,Image resolution,Superresolution,Texture synthesis,Texture filtering | Journal |
Volume | Issue | ISSN |
46 | C | 0923-5965 |
Citations | PageRank | References |
2 | 0.35 | 31 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seok Bong Yoo | 1 | 17 | 3.11 |
Kyuha Choi | 2 | 44 | 5.32 |
Young Woo Jeon | 3 | 2 | 0.35 |
Jong Beom Ra | 4 | 476 | 66.96 |