Recent years have witnessed the great success of image super-resolution based on deep learning. However, it is hard to adapt a well-trained deep model for a specific image for further improvement. Since the internal repetition of patterns is widely observed in visual entities, internal self-similarity is expected to help improve image super-resolution. In this paper, we focus on exploiting a complementary relation between external and internal example-based super-resolution methods. Specifically, we first develop a basic network learning external prior from large scale training data and then learn the internal prior from the given low-resolution image for task adaptation. By simply embedding a few additional layers into a pre-trained deep neural network, the image-adaptive super-resolution method exploits the internal prior for a specific image, and the external prior from a well-trained super-resolution model. We achieve 0.18 dB PSNR improvements over the basic network’s results on standard datasets. Extensive experiments under image super-resolution tasks demonstrate that the proposed method is flexible and can be integrated with lightweight networks. The proposed method boosts the performance for images with repetitive structures, and it improves the accuracy of the reconstructed image of the lightweight model.

中文翻译：

---

基于自适应特征变换的图像超分辨率内部学习

近年来，基于深度学习的图像超分辨率取得了巨大成功。然而，很难为特定图像调整训练有素的深度模型以进一步改进。由于在视觉实体中广泛观察到模式的内部重复，因此内部自相似性有望帮助提高图像超分辨率。在本文中，我们专注于利用外部和内部基于示例的超分辨率方法之间的互补关系。具体来说，我们首先从大规模训练数据中开发一个基本的网络学习外部先验，然后从给定的低分辨率图像中学习内部先验以进行任务适应。通过简单地将几个附加层嵌入到预先训练的深度神经网络中，图像自适应超分辨率方法利用特定图像的内部先验，以及来自训练有素的超分辨率模型的外部先验。我们在标准数据集上的基本网络结果上实现了 0.18 dB PSNR 改进。在图像超分辨率任务下的大量实验表明，所提出的方法是灵活的，可以与轻量级网络集成。所提出的方法提高了具有重复结构的图像的性能，并提高了轻量级模型重建图像的准确性。