Accurate Image Super-resolution Research Articles

Two-branch crisscross network for realistic and accurate image super-resolution

Convolutional Neural Networks have made remarkable progress in single-image super-resolution. However, existing methods struggle to balance reconstruction accuracy and perceptual quality, resulting in unsatisfactory outcomes. To address this challenge, we propose the Two-Branch Crisscross Generative Adversarial Network (TBCGAN) for achieving accurate and realistic super-resolution results. TBCGAN employs two asymmetric branches that separately reconstruct high-frequency (HF) and low-frequency (LF) images, leveraging their distinct information and reconstruction requirements. To ensure coherent results, we apply different supervision to the reconstructed HF, LF, and super-resolution (SR) images while facilitating information interaction through the interleaving and fusion of HF and LF features. Extensive experimental evaluations demonstrate that TBCGAN achieves an excellent balance between reconstruction accuracy and perceptual quality, outperforming GAN-based methods in reconstruction accuracy and MSE-based methods in perceptual quality.

Deep Learning-Based Wildfire Image Detection and Classification Systems for Controlling Biomass

Forests are essential natural resources that directly impact the ecosystem. However, the rising frequency of forest fires due to natural and artificial climate change has become a critical issue. A revolutionary municipal application proposes deploying an artificial intelligence-based forest fire warning system to prevent major disasters. This work aims to present an overview of vision-based methods for detecting and categorizing forest fires. The study employs a forest fire detection dataset to address the classification difficulty of discriminating between photos with and without fire. This method is based on convolutional neural network transfer learning with Inception-v3. Thus, automatic identification of current forest fires (including burning biomass) is a critical field of research for reducing negative repercussions. Early fire detection can also assist decision-makers in developing mitigation and extinguishment strategies. Radial basis function Networks (RBFNs) with rapid and accurate image super resolution (RAISR) is a deep learning framework trained on an input dataset to detect active fires and burning biomass. The proposed RBFN-RAISR model’s performance in recognizing fires and nonfires was compared to earlier CNN models using several performance criteria. The water wave optimization technique is used for image feature selection, noise and blurring reduction, image improvement and restoration, and image enhancement and restoration. When classifying fire and no-fire photos, the proposed RBFN-RAISR fire detection approach achieves 97.55% accuracy, 93.33% F-Score, 96.44% recall, 94.19% precision, and an error rate of 24.89. Given the one-of-a-kind forest fire detection dataset, the suggested method achieves promising results for the forest fire categorization problem.

SCN: Self-Calibration Network for fast and accurate image super-resolution

SCN: Self-Calibration Network for fast and accurate image super-resolution

Feature similarity rank-based information distillation network for lightweight image superresolution

To explore a fast and accurate image superresolution (SR) algorithm for real-world scenarios, information distillation is used to compress the number of feature channels, which has become one of the most commonly used tools in the field of lightweight image SR. However, existing information distillation-based image SR methods simply distill the first (distilled rate) channels in which many channels with unique features, i.e., low-redundancy features, are distilled as well. Hence, these methods lead to suboptimal SR performance since low-redundancy features are indispensable for image SR reconstruction. To alleviate this issue, this paper proposes a feature similarity ranking algorithm, which sorts the extracted feature channels according to the degree of channel redundancy. Then, it utilizes the ranked information distillation block (RIDB) for distilling high-redundancy features. In addition, considering that feature channels have already been sorted in the channel dimension, it involves a gated nonlocal attention module (GNLM) to capture the long-distance feature correlation in the spatial dimension. GNLM greatly reduces the computational consumption through the partitioned nonlocal module as well as the gate unit for evaluating the importance of each module, which is more suitable for lightweight image SR. Extensive experiments demonstrate that the proposed method performs favorably in terms of SR performance compared with not only information distillation-based image SR methods but also other state-of-the-art lightweight SR methods.

Lite-SRGAN and Lite-UNet: Toward Fast and Accurate Image Super-Resolution, Segmentation, and Localization for Plant Leaf Diseases

Lite-SRGAN and Lite-UNet: Toward Fast and Accurate Image Super-Resolution, Segmentation, and Localization for Plant Leaf Diseases

Attention Network with Information Distillation for Super-Resolution.

Resolution is an intuitive assessment for the visual quality of images, which is limited by physical devices. Recently, image super-resolution (SR) models based on deep convolutional neural networks (CNNs) have made significant progress. However, most existing SR models require high computational costs with network depth, hindering practical application. In addition, these models treat intermediate features equally and rarely explore the discriminative capacity hidden in their abundant features. To tackle these issues, we propose an attention network with information distillation(AIDN) for efficient and accurate image super-resolution, which adaptively modulates the feature responses by modeling the interactions between channel dimension and spatial features. Specifically, gated channel transformation (GCT) is introduced to gather global contextual information among different channels to modulate intermediate high-level features. Moreover, a recalibrated attention module (RAM) is proposed to rescale these feature responses, and RAM concentrates the essential contents around spatial locations. Benefiting from the gated channel transformation and spatial information masks working jointly, our proposed AIDN can obtain a more powerful ability to identify information. It effectively improves computational efficiency while improving reconstruction accuracy. Comprehensive quantitative and qualitative evaluations demonstrate that our AIDN outperforms state-of-the-art models in terms of reconstruction performance and visual quality.

Lightweight feature separation, fusion and optimization networks for accurate image super-resolution

Lightweight feature separation, fusion and optimization networks for accurate image super-resolution

URNet: A U-Shaped Residual Network for Lightweight Image Super-Resolution

It is extremely important and necessary for low computing power or portable devices to design more lightweight algorithms for image super-resolution (SR). Recently, most SR methods have achieved outstanding performance by sacrificing computational cost and memory storage, or vice versa. To address this problem, we introduce a lightweight U-shaped residual network (URNet) for fast and accurate image SR. Specifically, we propose a more effective feature distillation pyramid residual group (FDPRG) to extract features from low-resolution images. The FDPRG can effectively reuse the learned features with dense shortcuts and capture multi-scale information with a cascaded feature pyramid block. Based on the U-shaped structure, we utilize a step-by-step fusion strategy to improve the performance of feature fusion of different blocks. This strategy is different from the general SR methods which only use a single Concat operation to fuse the features of all basic blocks. Moreover, a lightweight asymmetric residual non-local block is proposed to model the global context information and further improve the performance of SR. Finally, a high-frequency loss function is designed to alleviate smoothing image details caused by pixel-wise loss. Simultaneously, the proposed modules and high-frequency loss function can be easily plugged into multiple mature architectures to improve the performance of SR. Extensive experiments on multiple natural image datasets and remote sensing image datasets show the URNet achieves a better trade-off between image SR performance and model complexity against other state-of-the-art SR methods.

Improved image denoising via RAISR with fewer filters

In recent years, accurate Gaussian noise removal has attracted considerable attention for mobile applications, as in smart phones. Accurate conventional denoising methods have the potential ability to improve denoising performance with no additional time. Therefore, we propose a rapid post-processing method for Gaussian noise removal in this paper. Block matching and 3D filtering and weighted nuclear norm minimization are utilized to suppress noise. Although these nonlocal image denoising methods have quantitatively high performance, some fine image details are lacking due to the loss of high frequency information. To tackle this problem, an improvement to the pioneering RAISR approach (rapid and accurate image super-resolution), is applied to rapidly post-process the denoised image. It gives performance comparable to state-of-the-art super-resolution techniques at low computational cost, preserving important image structures well. Our modification is to reduce the hash classes for the patches extracted from the denoised image and the pixels from the ground truth to 18 filters by two improvements: geometric conversion and reduction of the strength classes. In addition, following RAISR, the census transform is exploited by blending the image processed by noise removal methods with the filtered one to achieve artifact-free results. Experimental results demonstrate that higher quality and more pleasant visual results can be achieved than by other methods, efficiently and with low memory requirements.

Weighted SRGAN and Reconstruction Loss Analysis for Accurate Image Super Resolution

Super resolution (SR) image generation is to generate a high-resolution image from a given low-resolution image, which can be used in numerous vision tasks, such as small object detection and specific image processing. Generative adversarial network for super resolution (SRGAN) is the mainstream framework in SR task, which utilizes two reconstruction losses, including MSE loss and VGG loss. However, the influence of these losses on model learning is not examined. In this paper, the importance of MSE and VGG losses is analyzed. The loss function of traditional SRGAN is improved, and the weights of MSE and VGG losses are set manually. The weights range from 0 to 1, and the sampling interval is 0.1. Furthermore, a learnable parameter to dynamically adjust the two weights is proposed. Experiments on the datasets, including Set5, Set14, BAS100, and Urban100, show that our method is capable of generating much better images than SRGAN, with higher values of PSNR and SSIM. It is found that the MSE loss makes a greater contribution to learning the discriminative model and the VGG loss plays a supplementary role. Our WSRGAN can apply to most SRGAN-based methods to improve their accuracy.

Wide activation for accurate and fast computed tomography reconstruction in limited-angle problem

Computed Tomography (CT) has a wide range of applications in medical field. There are cases where the X-ray projection data is completely missing at some angles due to various reasons such as physical limitation. The traditional filtered back projection (FBP) algorithm has serious artifacts in the reconstructed image when the projection data is insufficient. While the iterative algorithm has better resolution, the computational complexity of the iterative algorithm far exceeds the FBP algorithm. In view of the contradiction between the precision and speed, the goal of this paper is to use neural networks combined with traditional algorithm FBP to get better results. Inspired by WDSR (Wide Activation for Efficient and Accurate Image Super-Resolution) network, we proposed WDCT network for CT reconstruction. Compared to WDSR, WDCT does not contain pixel shuffling and its input is the whole grayscale image instead of a cropped RGB image. We use WDCT network to enhance the image obtained by the FBP algorithm to reduce artifacts and accurately show details. The experimental results with WDCT network produce a superior performance in terms of artifact reduction and feature preservation. Meanwhile, it only takes about 0.3s to obtain an enhanced image reconstructed by FBP algorithm. In addition, we compare the effects of different structures of our neural network and discuss the performance of the neural network in our methods.

Accurate image super-resolution using dense connections and dimension reduction network

Recently, the convolution neural network (CNN) has achieved significant performance improvements toward the image Super-Resolution (SR) problems. Yet, the existing benchmark arts exist multiple limitations, including make use of the feature information deficiently, accompany with the gradient disappearance phenomenon and have serious time consumption. The paper utilizes a newly designed fully convolutional neural network named Accurate Image Super-resolution Using Dense Connections and Dimension Reduction Network (DCDRN) to fully exploit the image features. Contextual information of image regions utilizes efficiently and accurately through uniting dense connections and cascading small filters multiple times. And such implementation can be regarded as feature extractors to fuse local and global image features. We newly introduce 1 × 1 CNNs parallelization structure in the image reconstruction section to reduce data dimensions of the previous layers, which alleviates the computational burden effectively while avoiding the context info losing. The calculation becomes more complex and the convergence becomes slower during training because of the pre-processed images. The proposed DCDRN invents a simple and effective method which processes the original image directly and the optimization of layers and filters of CNNs shorten the cost of training significantly. Experiments on benchmark datasets with different methods show that DCDRN achieves gratifying performance against state-of-the-art methods. Code is available at .

SCRSR: An efficient recursive convolutional neural network for fast and accurate image super-resolution

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution (SR). These CNN networks effectively recover a high-resolution (HR) image from a low-resolution (LR) image, at the cost of enormous parameters and heavy computational burden. In this work, we propose a recursive efficient deep convolutional network for fast and accurate single-image SR with only 0.28M parameters. A Split-Concatenate-Residual (SCR) block is proposed to reduce computation and parameters. With downsampling block and upsampling block, we significantly reduce computational complexity and enlarge the size of the receptive field. Specifically, two-level recursive learning is proposed which can improve accuracy by increasing depth without adding any weight parameters. We also employ local, semi-global and global residual techniques to train our very deep network steadily and improve its performance. Extensive experiments indicate that our proposed method Split-Concatenate-Residual Super Resolution (SCRSR) yields promising SR performance while maintaining shorter running time and fewer parameters.

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks.

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of run-time and image quality.

RAISR: Rapid and Accurate Image Super Resolution

Given an image, we wish to produce an image of larger size with significantly more pixels and higher image quality. This is generally known as the single image super-resolution problem. The idea is that with sufficient training data (corresponding pairs of low and high resolution images) we can learn set of filters (i.e., a mapping) that when applied to given image that is not in the training set, will produce a higher resolution version of it, where the learning is preferably low complexity. In our proposed approach, the run-time is more than one to two orders of magnitude faster than the best competing methods currently available, while producing results comparable or better than state-of-the-art. A closely related topic is image sharpening and contrast enhancement, i.e., improving the visual quality of a blurry image by amplifying the underlying details (a wide range of frequencies). Our approach additionally includes an extremely efficient way to produce an image that is significantly sharper than the input blurry one, without introducing artifacts, such as halos and noise amplification. We illustrate how this effective sharpening algorithm, in addition to being of independent interest, can be used as a preprocessing step to induce the learning of more effective upscaling filters with built-in sharpening and contrast enhancement effect.