Network For Deblurring Research Articles

Motion Blur Removal for Uav-Based Wind Turbine Blade Images Using Synthetic Datasets

Unmanned air vehicle (UAV) based imaging has been an attractive technology to be used for wind turbine blades (WTBs) monitoring. In such applications, image motion blur is a challenging problem which means that motion deblurring is of great significance in the monitoring of running WTBs. However, an embarrassing fact for these applications is the lack of sufficient WTB images, which should include better pairs of sharp images and blurred images captured under the same conditions for network model training. To overcome the challenge of image pair acquisition, a training sample synthesis method is proposed. Sharp images of static WTBs were first captured, and then video sequences were prepared by running WTBs at different speeds. The blurred images were identified from the video sequences and matched to the sharp images using image difference. To expand the sample dataset, rotational motion blurs were simulated on different WTBs. Synthetic image pairs were then produced by fusing sharp images and images of simulated blurs. Finally, a total of 4000 image pairs were obtained. To conduct motion deblurring, a hybrid deblurring network integrated with DeblurGAN and DeblurGANv2 was deployed. The results show that the integration of DeblurGANv2 and Inception-ResNet-v2 provides better deblurred images, in terms of both metrics of signal-to-noise ratio (80.138) and structural similarity (0.950) than those obtained from the comparable networks of DeblurGAN and MobileNet-DeblurGANv2.

Recurrent Video Deblurring with Blur-Invariant Motion Estimation and Pixel Volumes

For the success of video deblurring, it is essential to utilize information from neighboring frames. Most state-of-the-art video deblurring methods adopt motion compensation between video frames to aggregate information from multiple frames that can help deblur a target frame. However, the motion compensation methods adopted by previous deblurring methods are not blur-invariant, and consequently, their accuracy is limited for blurry frames with different blur amounts. To alleviate this problem, we propose two novel approaches to deblur videos by effectively aggregating information from multiple video frames. First, we present blur-invariant motion estimation learning to improve motion estimation accuracy between blurry frames. Second, for motion compensation, instead of aligning frames by warping with estimated motions, we use a pixel volume that contains candidate sharp pixels to resolve motion estimation errors. We combine these two processes to propose an effective recurrent video deblurring network that fully exploits deblurred previous frames. Experiments show that our method achieves the state-of-the-art performance both quantitatively and qualitatively compared to recent methods that use deep learning.

A Lightweight Fusion Distillation Network for Image Deblurring and Deraining.

Recently, deep learning-based image deblurring and deraining have been well developed. However, most of these methods fail to distill the useful features. What is more, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from a high computational burden. We propose a lightweight fusion distillation network (LFDN) for image deblurring and deraining to solve the above problems. The proposed LFDN is designed as an encoder–decoder architecture. In the encoding stage, the image feature is reduced to various small-scale spaces for multi-scale information extraction and fusion without much information loss. Then, a feature distillation normalization block is designed at the beginning of the decoding stage, which enables the network to distill and screen valuable channel information of feature maps continuously. Besides, an information fusion strategy between distillation modules and feature channels is also carried out by the attention mechanism. By fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring and deraining results with a smaller number of parameters and outperform the existing methods in model complexity.

Learn from the past – sequentially one-to-one video deblurring network

With the growing availability of hand-held cameras in recent years, more and more images and videos are taken at any time and any place. However, they usually suffer from undesirable blur due to camera shake or object motion in the scene. In recent years, a few modern video deblurring methods are proposed and achieve impressive performance. However, they are still not suitable for practical applications as high computational cost or using future information as input. To address the issues, we propose a sequentially one-to-one video deblurring network (SOON) which can deblur effectively without any future information. It transfers both spatial and temporal information to the next frame by utilizing the recurrent architecture. In addition, we design a novel Spatio-Temporal Attention module to nudge the network to focus on the meaningful and essential features in the past. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art deblurring methods, both quantitatively and qualitatively, on various challenging real-world deblurring datasets. Moreover, as our method deblurs in an online manner and is potentially real-time, it is more suitable for practical applications.

SharpGAN: Dynamic Scene Deblurring Method for Smart Ship Based on Receptive Field Block and Generative Adversarial Networks.

Complex marine environment has an adverse effect on the object detection algorithm based on the vision sensor for the smart ship sailing at sea. In order to eliminate the motion blur in the images during the navigation of the smart ship and ensure safety, we propose SharpGAN, a new image deblurring method based on the generative adversarial network (GAN). First of all, we introduce the receptive field block net (RFBNet) to the deblurring network to enhance the network’s ability to extract blurred image features. Secondly, we propose a feature loss that combines different levels of image features to guide the network to perform higher-quality deblurring and improve the feature similarity between the restored images and the sharp images. Besides, we use the lightweight RFB-s module to significantly improve the real-time performance of the deblurring network. Compared with the existing deblurring methods, the proposed method not only has better deblurring performance in subjective visual effects and objective evaluation criteria, but also has higher deblurring efficiency. Finally, the experimental results reveal that the SharpGAN has a high correlation with the deblurring methods based on the physical model.

Color correction and restoration based on multi-scale recursive network for underwater optical image

Underwater image processing has played an important role in various fields such as submarine terrain scanning, submarine communication cable laying, underwater vehicles, underwater search and rescue. However, there are many difficulties in the process of acquiring underwater images. Specifically, the water body will selectively absorb part of the light when light travels through the water, resulting in color degradation of underwater images. At the same time, due to the influence of floating substances in the water, the light has a certain degree of scattering, which will bring serious problems such as blurred details and low contrast to underwater images. Therefore, using image processing technology to restore the real appearance of underwater images has a high practical value. In order to solve the above problems, we combine the color correction method with the deblurring network to improve the quality of underwater images in this paper. Firstly, aiming at the problem of insufficient number and diversity of underwater image samples, a network combined with depth image reconstruction and underwater image generation is proposed to simulate underwater images based on the style transfer method. Secondly, for the problem of color distortion, we propose a dynamic threshold color correction method based on image global information combined with the loss law of light propagation in water. Finally, in order to solve the problem of image blurring caused by scattering and further improve the overall image clarity, the color-corrected image is reconstructed by a multi-scale recursive convolutional neural network. Experiment results show that we can obtain images closer to underwater style with shorter training time. Compared with several latest underwater image processing methods, the proposed method has obvious advantages in multiple underwater scenes. Simultaneously, we can restore the color information, remove blurring and boost detail for underwater images.

Motion Blur Removal With Quality Assessment Guidance

Non-uniform blind motion deblurring is a challenging yet fundamental task in the computer vision field, which aims to restore the latent sharp image from the blurry input. Recently, deep-learning-based methods have made significant improvement and progress, on the metric of PSNR. They achieve good results mainly because they adopt Mean Squared Error (MSE) as the optimization objective, in addition to their good model design. However, simple adoption of the PSNR metric and the MSE loss, has non-ignorable disadvantages. PSNR cannot always succeed in assessing the deblurred quality in accordance with the human visual system (HVS), and MSE guides the network to generate over-smoothed images. To address these problems, we are the first to propose the deep-learning-based multi-scale non-reference quality assessment network (Deep DEBLUR-IQA) for assessing the quality of deblurred results. Moreover, a deblurring network of high efficiency is presented. It is more than 50 times faster than other SOTA multi-scale Convolution Neural Network (CNN) methods, with the newly propose Residual Dilated Block (RDB) and Light ResBlock (LRB). The deblurring network's performance can be further boosted with Multiple Dilation Block (MDB), with an acceptable speed decrease. Finally, and most importantly, we are the first to let Deep DEBLUR-IQA guide the deblurring network's optimization. This IQA-guided enhancement paradigm can significantly improve the deblurring results’ subjective quality while achieving excellent PSNR. Experimental results demonstrate that the proposed method performs favorably against state-of-the-art methods quantitatively and qualitatively.

A Two-Stage Network for Image Deblurring

Blind deblurring is a typical challenge in image processing, carried out to correct various complex types of distortions that occur in the real world. Although learning-based deblurring methods have substantially outperformed the traditional algorithms, they fail to make full use of image priors, leading to inconsistent data distributions between the restored images and sharp images. In this paper, we divide the deblurring process into two steps and propose a two-stage network. The first stage generates an initial deblurred image using a common convolutional network. The second stage converts the initial data distribution into a latent sharp image distribution to obtain sharp edges through a prior network. Moreover, we propose a relativistic training strategy to train the prior network, which aims to learn the latent sharp image priors. In addition, we use a coarse-to-fine multiscale framework that shares weights between the different scales. The experimental results show that compared with other state-of-the-art methods, our method achieves competitive performances on benchmark datasets.

Structure-Aware Motion Deblurring Using Multi-Adversarial Optimized CycleGAN.

Recently, Convolutional Neural Networks (CNNs) have achieved great improvements in blind image motion deblurring. However, most existing image deblurring methods require a large amount of paired training data and fail to maintain satisfactory structural information, which greatly limits their application scope. In this paper, we present an unsupervised image deblurring method based on a multi-adversarial optimized cycle-consistent generative adversarial network (CycleGAN). Although original CycleGAN can handle unpaired training data well, the generated high-resolution images are probable to lose content and structure information. To solve this problem, we utilize a multi-adversarial mechanism based on CycleGAN for blind motion deblurring to generate high-resolution images iteratively. In this multi-adversarial manner, the hidden layers of the generator are gradually supervised, and the implicit refinement is carried out to generate high-resolution images continuously. Meanwhile, we also introduce the structure-aware mechanism to enhance the structure and detail retention ability of the multi-adversarial network for deblurring by taking the edge map as guidance information and adding multi-scale edge constraint functions. Our approach not only avoids the strict need for paired training data and the errors caused by blur kernel estimation, but also maintains the structural information better with multi-adversarial learning and structure-aware mechanism. Comprehensive experiments on several benchmarks have shown that our approach prevails the state-of-the-art methods for blind image motion deblurring.

A deep convolutional neural network for simultaneous denoising and deblurring in computed tomography

Computed tomography (CT) has been commonly used for providing medical images. However, CT scans have a potential risk of side-effect due to high radiation dose. In order to overcome this limitation, low-dose CT imaging techniques have been developed by using novel scanners, reconstruction algorithms and adjusted scanning protocols. In spite of these strategies, the conventional low-dose CT imaging techniques are hard to compromise between radiation dose and image quality, leading to noise, blur and artifacts in CT images. These drawbacks of the conventional techniques degrade diagnostic accuracy. In this study, we proposed a deep convolutional neural network (CNN)-based low-dose CT imaging technique for simultaneously reducing noise and blur at once. The proposed method, called denoising and deblurring CNN (DnDbCNN), consisted of two networks, and each network was separately trained for reducing noise and blur in CT images. For combining the trained networks, a convolutional layer was added between the two trained networks, and the combined network was re-trained to update the weights of each layer. Denoising convolutional neural network (DnCNN) and super-resolution convolutional neural network (SRCNN) were also implemented for comparison. We evaluated the performance of the DnDbCNN in terms of mean-square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), coefficient-of-variation (COV) and modulation transfer function (MTF). The results showed that the DnDbCNN improved the noise property, spatial resolution and quantitative accuracy of CT images, and the performance of the DnDbCNN was superior to the conventional methods. As a result, the DnDbCNN can simultaneously reduce noise and blur by combining two networks through three training steps. Therefore, the DnDbCNN has a potential for improving CT image quality with low radiation dose and enables precise diagnosis.

Attention-based interpolation network for video deblurring

Video deblurring is a challenging low-level vision task due to variant blur artifacts caused by factors such as depth variations, high-speed movements and camera shakes. Although significant efforts have been devoted to addressing this task, two challenges of capturing temporal patterns and spatial topologies still remain. In this paper, an attention-based interframe compensation scheme is proposed to address the first challenge. The proposed scheme replaces frames in blurry sequences with newly restored frames, and estimates temporal patterns among the replaced sequence to restore the whole sequence. After each replacement, an attention block is employed to exploit dependencies among restored and blurry frames to capture stable temporal patterns. To tackle the second challenge, we propose an adaptive residual block that dynamically fuses multi-level features via learning location-specific weights. Comprehensive experimental results demonstrate that the proposed method achieves state-of-the-art performance in terms of accuracy, visual effect and model size.

Bi-branch network for dynamic scene deblurring

We present a bi-branch network for efficient dynamic scene deblurring. The challenge is to simultaneously reduce the computational cost and enhance the restoration accuracy. The proposed network conduct heterogeneous transformations on motion and RGB content in an encoder–decoder structure with skip connections. The computational efficiency is achieved by explicitly decomposing the intertwined mapping of spatiotemporal and cross-channel correlations into the motion branch that processes grayscale frames with our proposed pseudo depth-wise separable 3D convolution and the color branch that conducts depth-wise separable 2D convolution on RGB content. We refine features captured by the motion branch and the color branch by incorporating a lightweight nonlocal fusion layer that adapts the double attention operation to aggregate heterogeneous transformations and generate for each location in the feature space an output based on its correlation with the entire video clip. Our nonlocal fusion maintains low computational cost in processing high-resolution frames and operates in a patch-based manner during inference. The proposed architecture strikes the right balance between complexity and accuracy for dynamic scene deblurring. In comparison with state-of-the-art methods, the proposed network is compact and shows competitive restoration accuracy with a significant reduction in computational cost.

Exploiting Semantics for Face Image Deblurring

In this paper, we propose an effective and efficient face deblurring algorithm by exploiting semantic cues via deep convolutional neural networks. As the human faces are highly structured and share unified facial components (e.g., eyes and mouths), such semantic information provides a strong prior for restoration. We incorporate face semantic labels as input priors and propose an adaptive structural loss to regularize facial local structures within an end-to-end deep convolutional neural network. Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face image. We then adopt a parsing network to extract the semantic features from the coarse deblurred image. Finally, the fine deblurring network utilizes the semantic information to restore a clear face image. We train the network with perceptual and adversarial losses to generate photo-realistic results. The proposed method restores sharp images with more accurate facial features and details. Quantitative and qualitative evaluations demonstrate that the proposed face deblurring algorithm performs favorably against the state-of-the-art methods in terms of restoration quality, face recognition and execution speed.

Attention Network for Non-Uniform Deblurring

Recently, image deblurring task is valuable and challenging in computer vision. However, existing learning-based methods can not produce satisfactory results, such as lacking of salient structures and fine details. In this paper, we propose a solution to transform spatially variant blurry images into the photo-realistic sharp manifold. In this paper, we investigate an attention network for image deblurring. Instead of relying on local receptive fields to construct features by previous state-of-the-art methods, the non-local features for capturing long-range dependencies and the local features rely on receptive fields should be jointly considered. Therefore, we propose a novel dense feature fusion block that consists of a channel attention module and a pixel attention module. In addition, we further densely connected multiple dense feature fusion blocks to acquire high-order feature representation. Moreover, a scale attention module is further introduced for removing unfavorable features while retaining features that facilitate image recovery. Comprehensive experimental results show that our method is able to generate photo-realistic sharp images from real-world blurring images and outperforms state-of-the-art methods.

Video Deblurring via Temporally and Spatially Variant Recurrent Neural Network

The camera shake and high-speed motion of objects often produce a blurry video. However, it is hard to recover sharp videos using existing single or multiple image deblurring methods, as the blur artifacts in blurry videos are both temporally and spatially varying. In this paper, we propose a temporally and spatially variant recurrent neural network for video deblurring, in which both temporally and spatially variants employ ConvGRU blocks and a weight generator to capture spatio-temporal features. Meanwhile, the proposed model is trained in an end-to-end manner, where the model input and output are set to the same number. Thus, our model does not reduce the number of frames both in training and testing stages, which is important in practical applications. Quantitative and qualitative evaluations on standard benchmark datasets demonstrate that the proposed method outperforms the current state-of-the-art methods.

Efficient and Interpretable Deep Blind Image Deblurring Via Algorithm Unrolling

Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced performance. That said, neural network approaches are generally empirically designed and the underlying structures are difficult to interpret. In recent years, a promising technique called algorithm unrolling has been developed that has helped connect iterative algorithms such as those for sparse coding to neural network architectures. In this article, we propose a neural network architecture based on this idea. We first present an iterative algorithm that may be considered as a generalization of the traditional total-variation regularization method in the gradient domain. We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID). Key algorithm parameters are learned with the help of training images. Our proposed deep network DUBLID achieves significant practical performance gains while enjoying interpretability and efficiency at the same time. Extensive experimental results show that DUBLID outperforms many state-of-the-art methods and in addition is computationally faster.

Deep Recurrent Network for Fast and Full-Resolution Light Field Deblurring

Restoring a sharp light field image from its blurry input has become essential due to the increasing popularity of parallax-based image processing. State-of-the-art blind light field deblurring methods suffer from several issues such as slow processing, reduced spatial size, and a limited motion blur model. In this work, we address these challenging problems by generating a complex blurry light field dataset and proposing a learning-based deblurring approach. In particular, we model the full 6-degree of freedom (6-DOF) light field camera motion, which is used to create the blurry dataset using a combination of real light fields captured with a Lytro Illum camera, and synthetic light field renderings of 3D scenes. Furthermore, we propose a light field deblurring network that is built with the capability of large receptive fields. We also introduce a simple strategy of angular sampling to train on the large-scale blurry light field effectively. We evaluate our method through both quantitative and qualitative measurements and demonstrate superior performance compared to the state-of-the-art method with a massive speedup in execution time. Our method is about 16K times faster than Srinivasan et. al. [22] and can deblur a full-resolution light field in less than 2 seconds.

Adversarial Spatio-Temporal Learning for Video Deblurring.

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance.