Cross-domain heterogeneous residual network for single image super-resolution. (May 2022)

• Record Type: Journal Article
• Authors: Ji, Li; Zhu, Qinghui; Zhang, Yongqin; Yin, Juanjuan; Wei, Ruyi; Xiao, Jinsheng; Xiao, Deqiang; Zhao, Guoying
• Is Part Of: Neural networks. Volume 149(2022)
• Page Start: 84
• Page End: 94
• Publication Date: 2022-05
• Subjects: Neural networks -- Neural network architecture -- Image restoration -- Image resolution; Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2022.02.008
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: 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 .