School of Information Science and Technology, Northwest University, Xi'an 710127, China.
School of Information Science and Technology, Northwest University, Xi'an 710127, China; CAS Key Laboratory of Spectral Imaging Technology, Xi'an 710119, China.
Neural Netw. 2022 May;149:84-94. doi: 10.1016/j.neunet.2022.02.008. Epub 2022 Feb 11.
Single image super-resolution is an ill-posed problem, whose purpose is to acquire a high-resolution image from its degraded observation. Existing deep learning-based methods are compromised on their performance and speed due to the heavy design (i.e., huge model size) of networks. In this paper, we propose a novel high-performance cross-domain heterogeneous residual network for super-resolved image reconstruction. Our network models heterogeneous residuals between different feature layers by hierarchical residual learning. In outer residual learning, dual-domain enhancement modules extract the frequency-domain information to reinforce the space-domain features of network mapping. In middle residual learning, wide-activated residual-in-residual dense blocks are constructed by concatenating the outputs from previous blocks as the inputs into all subsequent blocks for better parameter efficacy. In inner residual learning, wide-activated residual attention blocks are introduced to capture direction- and location-aware feature maps. The proposed method was evaluated on four benchmark datasets, indicating that it can construct the high-quality super-resolved images and achieve the state-of-the-art performance. Code and pre-trained models are available at https://github.com/zhangyongqin/HRN.
单图像超分辨率是一个不适定问题，其目的是从降质观测中获取高分辨率图像。现有的基于深度学习的方法由于网络的繁重设计（即庞大的模型尺寸）而在性能和速度上受到限制。在本文中，我们提出了一种新颖的用于超分辨图像重建的高性能跨域异构残差网络。我们的网络通过分层残差学习对不同特征层之间的异构残差进行建模。在外层残差学习中，双域增强模块提取频域信息，以增强网络映射的空域特征。在中层残差学习中，通过将前一层的输出连接起来作为所有后续层的输入，构建宽激活残差残差密集块，以提高参数效率。在内层残差学习中，引入宽激活残差注意力块来捕获具有方向和位置感知的特征图。该方法在四个基准数据集上进行了评估，表明它可以构建高质量的超分辨图像，并达到最新的性能水平。代码和预训练模型可在 https://github.com/zhangyongqin/HRN 上获得。
