TSRGAN: Real-world text image super-resolution based on adversarial learning and triplet attention

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.

With the availability of commercial Light Field (LF) cameras, LF imaging has emerged as an up-and-coming technology in computational photography. However, the spatial resolution is significantly constrained in commercial micro-lens-based LF cameras because of the inherent multiplexing of spatial and angular information. Therefore, it becomes the main bottleneck for other applications of light field cameras. This paper proposes an adaptation module in a pre-trained Single Image Super-Resolution (SISR) network to leverage the powerful SISR model instead of using highly engineered light field imaging domain-specific Super Resolution models. The adaption module consists of a Sub-aperture Shift block and a fusion block. It is an adaptation in the SISR network to further exploit the spatial and angular information in LF images to improve the super-resolution performance. Experimental validation shows that the proposed method outperforms existing light field super-resolution algorithms. It also achieves PSNR gains of more than 1 dB across all the datasets as compared to the same pre-trained SISR models for scale factor 2, and PSNR gains 0.6 − 1 dB for scale factor 4.

B2GAN: Bidirectional-branch generative adversarial network for text image super-resolution with structure preservation

Single image super resolution is a very important computer vision task, with a wide range of applications. In recent years, the depth of the super-resolution model has been constantly increasing, but with a small increase in performance, it has brought a huge amount of computation and memory consumption. In this work, in order to make the super resolution models more effective, we proposed a novel single image super resolution method via recursive squeeze and excitation networks (SESR). By introducing the squeeze and excitation module, our SESR can model the interdependencies and relationships between channels and that makes our model more efficiency. In addition, the recursive structure and progressive reconstruction method in our model minimized the layers and parameters and enabled SESR to simultaneously train multi-scale super resolution in a single model. After evaluating on four benchmark test sets, our model is proved to be above the state-of-the-art methods in terms of speed and accuracy.

Adversarially trained deep neural networks have significantly improved performance of single image super resolution, by hallucinating photorealistic local textures, thereby greatly reducing the perception difference between a real high resolution image and its super resolved (SR) counterpart. However, application to medical imaging requires preservation of diagnostically relevant features while refraining from introducing any diagnostically confusing artifacts. We propose using a deep convolutional super resolution network (SRNet) trained for (i) minimising reconstruction loss between the real and SR images, and (ii) maximally confusing learned relativistic visual Turing test (rVTT) networks to discriminate between (a) pair of real and SR images (T1) and (b) pair of patches in real and SR selected from region of interest (T2). The adversarial loss of T1 and T2 while backpropagated through SRNet helps it learn to reconstruct pathorealism in the regions of interest such as white blood cells (WBC) in peripheral blood smears or epithelial cells in histopathology of cancerous biopsy tissues, which are experimentally demonstrated here. Experiments performed for measuring signal distortion loss using peak signal to noise ratio (pSNR) and structural similarity (SSIM) with variation of SR scale factors, impact of rVTT adversarial losses, and impact on reporting using SR on a commercially available artificial intelligence (AI) digital pathology system substantiate our claims.

These days, many methods have been proposed to deal with nature image super-resolution (SR) and get impressive performance. However, these methods don't do well in text images SR due to their ignorance of the difference between nature images and text images. In this paper, we propose a matting-based dual generative adversarial network (mdGAN) for text image SR. Firstly, the input image is decomposed into text, foreground and background layers using deep image matting. Then two parallel branches are constructed to recover text boundary information and color information respectively. Furthermore, in order to improve the restoration accuracy of characters in output image, we use the input image's corresponding ground truth text label as extra supervise information to refine the two-branch networks during training. Experiments on real text images demonstrate that our method outperforms several state-of-the-art methods quantitatively and qualitatively.

Recently, imaging systems have exhibited remarkable image restoration performance through optimized optical systems and deep-learning-based models. Despite advancements in optical systems and models, severe performance degradation occurs when the predefined optical blur kernel differs from the actual kernel while restoring and upscaling the images. This is because super-resolution (SR) models assume that a blur kernel is predefined and known. To address this problem, various lenses could be stacked, and the SR model could be trained with all available optical blur kernels. However, infinite optical blur kernels exist in reality; thus, this task requires the complexity of the lens, substantial model training time, and hardware overhead. To resolve this issue by focusing on the SR models, we propose a kernel-attentive weight modulation memory network by adaptively modulating SR weights according to the shape of the optical blur kernel. The modulation layers are incorporated into the SR architecture and dynamically modulate the weights according to the blur level. Extensive experiments reveal that the proposed method improves peak signal-to-noise ratio performance, with an average gain of 0.83 dB for blurred and downsampled images. An experiment with a real-world blur dataset demonstrates that the proposed method can handle real-world scenarios.

Abstract. As deep learning models advance, their use in Super Resolution (SR) tasks has become pivotal for enhancing remote sensing low-resolution (LR) satellite images. However, the decision making processes within these models remain opaque, especially in remote sensing applications where transparency is critical. This paper focuses on applying Explainable Artificial Intelligence (XAI) techniques, particularly Local Attribution Maps (LAMs), to analyze and interpret the internal behavior of both general purpose and remote sensing specific SR neural networks. General purpose models like Generative Adversarial Network for Super Resolution (SRGAN), Enhanced Deep Super-Resolution Network (EDSR), Efficient Super-Resolution Transformer (ESRT), and Hybrid-Attention Transformer (HAT), although highly effective in SR tasks, were originally designed for broader image enhancement challenges; in contrast, Hybrid-Scale Self-Similarity Exploitation Network (HSENet) and Multi-scale Enhanced Network (MEN) are tailored for the unique complexities of remote sensing, such as varied textures and intricate scene features. By leveraging LAMs, we highlight how different networks prioritize and process features such as edges, textures, and high frequency details to generate super resolved outputs. The comparative study between general purpose and remote sensing specific networks outlines each model’s strengths and weaknesses in managing the data present in remote sensing imagery. This approach addresses the previously unexplored application of LAMs in remote sensing for SR, contributing to the research in this field and providing deeper insights into the interpretability and transparency of widely used SR models. Furthermore, by drawing parallels between feature attribution in SR and classification tasks, we suggest new pathways for integrating semantic information to refine model transparency and performance in remote sensing applications.

Efficient deep learning based methods have achieved significant performance in single image super-resolution. Recent research on efficient super-resolution has mainly focused on reducing the number of parameters and computational complexity through various network designs, enabling models to be better deployed on resource constrained devices. In this work, we propose a novel and effective super-resolution model based on attention mechanism and structural re-parameterization, called Dual Path Attention and Re-parameterization Network DPARN , which uses a hybrid attention mechanisms to balance the running speed and reconstruction quality of the model. Specifically, we utilize grouped convolution to introduce both parameter free and enhanced spatial attention to improve the feature extraction capability of student networks. Meanwhile, we ado-pted a novel lightweight network training strategy that first uses knowledge distillation for initial training, during which structured knowledge from the teacher network is transmitted to the student network. Then, multiple loss functions are combined to fine-tuning the student network, in order to preserve high-frequency details and avoid excessive smoothing caused by pixel loss. Finally, extensive experiments conducted on four benchmark datasets demonstrated the effectiveness and efficiency of proposed DPARN. Our method achieves PSNR SSIM performance comparable to state-of-the-art efficient super-resolution models, with faster inference speed and fewer network parameters.

Single image super-resolution (SISR) with deep convolutional neural networks has recently attracted increasing attention due to its potentials to generate rich details. To obtain better fidelity and visual quality, most of existing methods are of heavy design with the depth of network. However, the lack of high-frequency information in the deep network and the limit of non-local context relations of pixels remain the core issue. In addition, there are many arbitrary-scale image super-resolution tasks, so it is a focus that provides an effective and efficient model for super resolution with arbitrary-scale. To this end, we propose a Feature Preserving and Enhancing Network (FPEN) based on implicit representation, which is aims to preserving high-frequency information in deep network and enhancing non-local contextual features of pixels to output more realistic images at arbitrary scales. In particular, our proposed High Frequency Preserving Block (HFPB) can divide the features into high-frequency components and low-frequency components, and allocate more operations to high-frequency components to ensure that high-frequency components can be preserved in the network. Since high-frequency information contains the details and texture of the image, it can restore the finer details of the image. Moreover, Pixel Continuity Attention (PiCA) module our proposed utilizes visual cues observed from pixels to adaptively recalibrate the pixel range that needs attention in the image to better achieve feature enhancement and generate smoother images. Extensive experiments conducted on benchmark SISR models and datasets show that Feature Preserving and Enhancing Network can be employed for various SISR tasks with arbitrary-scale to obtain the better visual quality than other state-of-the-art SR algorithms.

Self-supervised cycle-consistent learning for scale-arbitrary real-world single image super-resolution

Recently deep convolutional neural network (CNN) has made significant achievement in Single Image Super-Resolution (SISR). Most CNN-based SISR methods used the default L2 norm of the error. However, for Hyperspectral Image (HSI), this loss function may bring spectral inconsistencies. The main reason is that most methods did not pay much attention to spectral loss. To HSI, the loss function should capture not only spatial information but also spectral consistency. In this paper, a Multi-Losses Function Network (MLFN) simultaneously considering spatial and spectral information is proposed, and is composed of two parts: one is Concatenate Dense Residual Network (CDRN), and the other is Loss Network (LN). CDRN is an image reconstruction network which can utilize the hierarchical features extracted from the low-resolution image. LN includes pixel-wise spatial loss and spectral loss which drive the learning of the entire reconstruction model. The experimental results prove that the proposed MLFN can enhance spatial resolution with the consistency of the spectrum of HSI preserved.

Traditional works have shown that patches in a natural image tend to redundantly recur many times inside the image, both within the same scale, as well as across different scales. Make full use of these multi-scale information can improve the image restoration performance. However, the current proposed deep learning based restoration methods do not take the multi-scale information into account. In this paper, we propose a dilated convolution based inception module to learn multi-scale information and design a deep network for single image super-resolution. Different dilated convolution learns different scale feature, then the inception module concatenates all these features to fuse multi-scale information. In order to increase the reception field of our network to catch more contextual information, we cascade multiple inception modules to constitute a deep network to conduct single image super-resolution. With the novel dilated convolution based inception module, the proposed end-to-end single image super-resolution network can take advantage of multi-scale information to improve image super-resolution performance. Experimental results show that our proposed method outperforms many state-of-the-art single image super-resolution methods.

Tremendous progress has been witnessed on single image super-resolution (SR), where existing deep SR models achieve impressive performance in objective criteria, e.g., PSNR and SSIM. However, most of the SR methods are limited in visual perception, for example, they look too smooth. Generative adversarial network (GAN) favors SR visual effects over most of the deep SR models but is poor in objective criteria. In order to trade off the objective and subjective SR performance, we design a joint-attention discriminator with which GAN improves the SR performance in PSNR and SSIM, as well as maintaining the visual effect compared with non-attention GAN based SR models. The joint-attention discriminator contains dense channel-wise attention and cross-layer attention blocks. The former is applied in the shallow layers of the discriminator for channel-wise weighting combination of feature maps. The latter is employed to select feature maps in some middle and deep layers for effective discrimination. Extensive experiments are conducted on six benchmark datasets and the experimental results show that our proposed discriminator combining with different generators can achieve more realistic visual performances.

Deep convolutional neural networks (CNNs) are widely used in single image super-resolution (SISR) and provide remarkable performance. However, most existing CNN-based super-resolution (SR) models focus mainly on designing deep or wide architecture and neglect intended detail enhancement, thereby hindering the CNN representational capacity. To resolve this problem, we propose a multi-scale detail enhancement network (MS-DEN) for SISR. Specifically, we introduce a multi-scale detail extraction module (MS-DEM), which first converts features into a 3-channel simulation image, and then, directly extracts detail information from the simulation image space. Furthermore, we concatenate the 3-channel image and extracted detail image to generate detail-guided features. Subsequently, we propose a multi-context channel attention module (MC-CAM) to relatively better fuse local and global features, and enhance features containing discontinuous detail information. With detail enhancement, MS-DEN can restore highly accurate details and lead to performance improvement. Numerous experiments show that our MS-DEN achieves competitive performance against the state-of-the-art methods.