• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Acoustics, Speech and Signal Processing >Multi-scale Dense Network for Single-image Super-resolution
【24h】

Multi-scale Dense Network for Single-image Super-resolution

机译：用于单图像超分辨率的多尺度密集网络

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Recently, deep neural networks have led to tremendous advances in image super-resolution. As a well-known one-to-many inverse problem, the deep learning based methods tackle this issue via large receptive field. By that, the deep network could infer each output pixel from sufficient context information. However, most existing studies use larger kernel size or design a very deep network model to attain sufficient receptive field. The computational cost dramatically increments along with the training difficulty. Concerning this problem, the goal of this paper is to design an effective and trainable convolutional neural network. We proposed a multi-scale dense network (MSDN) which is composed of deep concatenation and basic blocks, namely multi-scale dense block (MSDB). The proposed MSDB use different dilated convolutions to gather multi-scale information; meanwhile concatenating the different dilated convolution results magnify the receptive field of a single layer. To facilitate the training difficulty, there are the dense skip connections in the proposed MSDB. Moreover, the deep concatenation and global skip connection are also adopted for improving training furthermore. Consequently, we achieve a large receptive field network without deeper structure. The experiments indicate that the quality of the proposed MSDN yields the state-of-the-art result.
机译：近来，深度神经网络已导致图像超分辨率的巨大进步。作为众所周知的一对多反问题，基于深度学习的方法通过较大的接受域来解决此问题。这样，深度网络可以从足够的上下文信息中推断每个输出像素。但是，大多数现有研究使用较大的内核大小或设计非常深的网络模型来获得足够的接收范围。计算成本随着训练难度而急剧增加。关于这个问题，本文的目的是设计一个有效且可训练的卷积神经网络。我们提出了一个由深层级联和基本块组成的多尺度密集网络（MSDN），即多尺度密集块（MSDB）。提议的MSDB使用不同的膨胀卷积来收集多尺度信息。同时，将不同的膨胀卷积结果串联起来，可以放大单层的接收场。为了减轻训练难度，建议的MSDB中存在密集的跳过连接。此外，还采用了深度级联和全局跳过连接来进一步改进训练。因此，我们实现了一个大型的接收现场网络，而没有更深层次的结构。实验表明，所提出的MSDN的质量产生了最新的结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号