arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.10488eess.IVcs.CVcs.LG
收藏

一种用于单帧图像超分辨率的两级注意网络

A Two-Stage Attentive Network for Single Image Super-Resolution

Dalian University of Technology(大连理工大学);JD Finance America Corporation(京东金融美国公司);Northwestern Polytechnical University(西北工业大学)

Jiqing Zhang, Chengjiang Long, Yuxin Wang, Haiyin Piao, Haiyang Mei, Xin Yang, Baocai Yin

摘要:

最近,深度卷积神经网络(CNN)在单图像超分辨率(SISR)中得到了广泛的研究,并取得了显着的进展。然而,大多数现有的基于CNN的SISR方法在特征提取阶段没有充分探索上下文信息,并且很少关注最终的高分辨率(HR)图像重建步骤,因此阻碍了期望的SR性能。为了解决上述两个问题,在本文中,我们提出了一个两阶段的注意网络(TSAN)的精确SISR在一个由粗到细的方式。具体来说,我们设计了一个新的多上下文注意块(MCAB),使网络专注于更多的信息上下文功能。此外,我们提出了一个必要的细化注意块(RAB),可以探索有用的线索,在HR空间重建精细详细的HR图像。在四个基准数据集上的广泛评估表明,我们提出的TSAN在定量指标和视觉效果方面的有效性。代码可在www.example.com上获得。

英文摘要:

Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore contextual information in the feature extraction stage and pay little attention to the final high-resolution (HR) image reconstruction step, hence hindering the desired SR performance. To address the above two issues, in this paper, we propose a two-stage attentive network (TSAN) for accurate SISR in a coarse-to-fine manner. Specifically, we design a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features. Moreover, we present an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image. Extensive evaluations on four benchmark datasets demonstrate the efficacy of our proposed TSAN in terms of quantitative metrics and visual effects. Code is available at https://github.com/Jee-King/TSAN.

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。

↑