arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.06779cs.CV
收藏

一种基于注意力的单幅图像超分辨率方法

An Attention-Based Approach for Single Image Super Resolution

Southeast University(东南大学);Nanjing Institute of Communications Technologies(南京通信技术研究院);Nanjing University(南京大学);Federation University Australia(澳大利亚联邦大学)

Yuan Liu, Yuancheng Wang, Nan Li, Xu Cheng, Yifeng Zhang, Yongming Huang, Guojun Lu

摘要:

单幅图像超分辨率(SISR)的主要挑战是对微小纹理等高频细节的恢复。然而,大多数最先进的方法缺乏特定的模块来识别高频区域,导致输出图像模糊。我们提出了一个基于注意力的方法,给纹理区域和光滑区域之间的歧视。在定位高频细节的位置之后,进行高频补偿。这种方法可以与以前提出的SISR网络。通过提供高频增强,实现更好的性能和视觉效果。我们还提出了自己的SISR网络组成的DenseRes块。该块提供了一种有效的方法来组合低级别特征和高级别特征。广泛的基准测试结果表明,我们提出的方法实现了显着的改善,在SISR的国家的最先进的作品。

英文摘要:

The main challenge of single image super resolution (SISR) is the recovery of high frequency details such as tiny textures. However, most of the state-of-the-art methods lack specific modules to identify high frequency areas, causing the output image to be blurred. We propose an attention-based approach to give a discrimination between texture areas and smooth areas. After the positions of high frequency details are located, high frequency compensation is carried out. This approach can incorporate with previously proposed SISR networks. By providing high frequency enhancement, better performance and visual effect are achieved. We also propose our own SISR network composed of DenseRes blocks. The block provides an effective way to combine the low level features and high level features. Extensive benchmark evaluation shows that our proposed method achieves significant improvement over the state-of-the-art works in SISR.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑