4.8 Article

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks

出版社

IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2018.2865304

关键词

Single-image super-resolution; deep convolutional neural networks; Laplacian pyramid

资金

  1. NSF CAREER [1149783]
  2. NSF [1755785]
  3. Direct For Computer & Info Scie & Enginr [1149783] Funding Source: National Science Foundation
  4. Direct For Computer & Info Scie & Enginr
  5. Div Of Information & Intelligent Systems [GRANTS:13953834] Funding Source: National Science Foundation
  6. Div Of Information & Intelligent Systems [1149783] Funding Source: National Science Foundation

向作者/读者索取更多资源

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据