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.

中文翻译：

---

利用深度拉普拉斯金字塔网络实现快速准确的图像超分辨率


卷积神经网络最近证明了单图像超分辨率的高质量重建。然而，现有方法通常需要大量网络参数，并且在运行时需要大量计算负载才能生成高精度超分辨率结果。在本文中，我们提出了深层拉普拉斯金字塔超分辨率网络，用于快速准确的图像超分辨率。所提出的网络逐步重建多个金字塔级别的高分辨率图像的子带残差。与涉及预处理的双三次插值（导致大特征图）的现有方法相比，所提出的方法直接从低分辨率输入空间中提取特征，因此计算负载较低。我们使用鲁棒的 Charbonnier 损失函数对所提出的网络进行深度监督训练，并实现高质量的图像重建。此外，我们利用递归层在金字塔级别之间以及内部共享参数，从而大大减少参数的数量。对基准数据集的广泛定量和定性评估表明，所提出的算法在运行时间和图像质量方面优于最先进的方法。