Multi-Resolution Space-Attended Residual Dense Network for Single Image Super-Resolution

Abstract

With the help of deep convolutional neural networks, a vast majority of single image superresolution (SISR) methods have been developed, and achieved promising performance. However, these methods suffer from over-smoothness in textured regions due to utilizing a single-resolution network to reconstruct both the low-frequency and high-frequency information simultaneously. To overcome this problem, we propose a Multi-resolution space-Attended Residual Dense Network (MARDN) to separate lowfrequency and high-frequency information for reconstructing high-quality super-resolved images. Specifically, we start from a low-resolution sub-network, and add low-to-high resolution sub-networks step by step in several stages. These sub-networks with different depth and resolution are utilized to produce feature maps of different frequencies in parallel. For instance, the high-resolution sub-network with fewer stages is applied to local high-frequency textured information extraction, while the low-resolution one with more stages is devoted to generating global low-frequency information. Furthermore, the fusion block with channelwise sub-network attention is proposed for adaptively fusing the feature maps from different sub-networks instead of applying concatenation and 1 × 1 convolution. A series of ablation investigations and model analyses validate the effectiveness and efficiency of our MARDN. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed MARDN against the state-of-the-art methods. Our super-resolution results and the source code can be downloaded from https://github.com/Periter/MARDN.

Memory‐ and time‐efficient dense network for single‐image super‐resolution

“…A visual comparison is shown in Figure 10 for models '128' and '512-128', and images 'img047' and 'img52' from [14,16] to compare with the state-ofthe-art. All networks are trained with 200 epochs, and the results are reported in Table 8.…”

“…Dense blocks of two recent dense CNNs are replaced with the proposed dense blocks [14,16] to compare with the state-ofthe-art. All networks are trained with 200 epochs, and the results are reported in Table 8.…”

“…Recent SISR methods have used either local [15][16][17] or global dense connections [18] in their proposed CNNs with promising results. Local dense connections are between convolutional layers [15,16] or residual units [17]. Utilising a larger growth rate enriches the concatenating feature-maps and leads to an overall superior discriminative ability.…”

Image quality enhancement using hybrid attention networks

“…In terms of its way of downsampling, anti-aliasing down-sampling [60] is adopted. Qin [61] et al also propose a similar network based on multi-resolution strategy while the attention is considered in the process of feature fusion. We follow this multi-resolution strategy and propose a basic block containing multi-scale branches so that it can efficiently balance spatial accuracy and contextual information.…”

Lightweight Feedback Convolution Neural Network for Remote Sensing Images Super-Resolution

“…So, how to restore low-resolution remote sensing images to high-resolution images through algorithms has become a current research hotspot. Super-resolution [1]- [4] not only restores sharpness from lower-resolution images, but also saves the cost of replacing or upgrading camera sensors because the super-resolution method is to process The associate editor coordinating the review of this manuscript and approving it for publication was Inês Domingues . the photos taken.…”