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 2008.13084eess.IVcs.CV
收藏

MDCN:多尺度密集交叉网络图像超分辨率

MDCN: Multi-scale Dense Cross Network for Image Super-Resolution

East China Normal University(华东师范大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))

Juncheng Li, Faming Fang, Jiaqian Li, Kangfu Mei, Guixu Zhang

摘要:

卷积神经网络已被证明是单图像超分辨率(SISR)的巨大好处。然而,以前的工作没有充分利用多尺度特征,忽略了不同上采样因子之间的尺度间相关性,导致性能次优。我们不是盲目地增加网络的深度,而是致力于挖掘图像特征并学习不同上采样因子之间的尺度间相关性。为了实现这一点,我们提出了一个多尺度密集交叉网络(MDCN),它实现了更少的参数和更少的执行时间的性能。MDCN由多尺度密集交叉块(MDCB)、层次特征提取块(HFDB)和动态重构块(DRB)组成。其中,MDCB旨在检测多尺度特征并最大限度地利用不同尺度下的图像特征流,HFDB专注于自适应地重新校准通道特征响应以实现特征蒸馏,DRB试图在单个模型中重建具有不同上采样因子的SR图像。值得注意的是,所有这些模块都可以独立运行。这意味着这些模块可以有选择地插入任何CNN模型,以提高模型性能。大量的实验表明,MDCN在SISR中取得了有竞争力的结果,特别是在多个上采样因子的重建任务中。代码将在https://github.com/MIVRC/MDCN-PyTorch上提供。

英文摘要:

Convolutional neural networks have been proven to be of great benefit for single-image super-resolution (SISR). However, previous works do not make full use of multi-scale features and ignore the inter-scale correlation between different upsampling factors, resulting in sub-optimal performance. Instead of blindly increasing the depth of the network, we are committed to mining image features and learning the inter-scale correlation between different upsampling factors. To achieve this, we propose a Multi-scale Dense Cross Network (MDCN), which achieves great performance with fewer parameters and less execution time. MDCN consists of multi-scale dense cross blocks (MDCBs), hierarchical feature distillation block (HFDB), and dynamic reconstruction block (DRB). Among them, MDCB aims to detect multi-scale features and maximize the use of image features flow at different scales, HFDB focuses on adaptively recalibrate channel-wise feature responses to achieve feature distillation, and DRB attempts to reconstruct SR images with different upsampling factors in a single model. It is worth noting that all these modules can run independently. It means that these modules can be selectively plugged into any CNN model to improve model performance. Extensive experiments show that MDCN achieves competitive results in SISR, especially in the reconstruction task with multiple upsampling factors. The code will be provided at https://github.com/MIVRC/MDCN-PyTorch.

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。

↑