Network For Deblurring Research Articles

MIMO-Uformer: A Transformer-Based Image Deblurring Network for Vehicle Surveillance Scenarios

Motion blur is a common problem in the field of surveillance scenarios, and it obstructs the acquisition of valuable information. Thanks to the success of deep learning, a sequence of CNN-based architecture has been designed for image deblurring and has made great progress. As another type of neural network, transformers have exhibited powerful deep representation learning and impressive performance based on high-level vision tasks. Transformer-based networks leverage self-attention to capture the long-range dependencies in the data, yet the computational complexity is quadratic to the spatial resolution, which makes transformers infeasible for the restoration of high-resolution images. In this article, we propose an efficient transformer-based deblurring network, named MIMO-Uformer, for vehicle-surveillance scenarios. The distinct feature of the MIMO-Uformer is that the basic-window-based multi-head self-attention (W-MSA) of the Swin transformer is employed to reduce the computational complexity and then incorporated into a multi-input and multi-output U-shaped network (MIMO-UNet). The performance can benefit from the operation of multi-scale images by MIMO-UNet. However, most deblurring networks are designed for global blur, while local blur is more common under vehicle-surveillance scenarios since the motion blur is primarily caused by local moving vehicles. Based on this observation, we further propose an Intersection over Patch (IoP) factor and a supervised morphological loss to improve the performance based on local blur. Extensive experiments on a public and a self-established dataset are carried out to verify the effectiveness. As a result, the deblurring behavior based on PSNR is improved at least 0.21 dB based on GOPRO and 0.74 dB based on the self-established datasets compared to the existing benchmarks.

Deep blind super-resolution for hyperspectral images

Current deep learning methods for single hyperspectral image super-resolution are non-blind ones, which adopt the simplistic bicubic degradation model. These models have poor generalization performance and cannot handle unknown degradation. Additionally, blind super-resolution methods for RGB images neglect rich spectral information in hyperspectral images, which causes spectral distortion in results. To address these issues, we consider the degeneration estimation and propose a single hyperspectral image blind super-resolution algorithm. Specifically, we first use a blur kernel estimation network and a deblurring network to obtain the image without blur. We change the receptive field by exchanging spatial channel information when estimating the kernel, thereby obtaining blurry information at different scales. In addition, to reduce the errors introduced by kernel mismatch and the relevant information among bands ignored by the group convolution, we fuse the spatial information of the blurred image to compensate for the errors and then utilize the spatial and spectral information of other bands to guide the feature extraction of the current band. Finally, we integrate the feature information from different branches in a global fusion network to improve spatial and spectral information fidelity further. Extensive experiments on synthetic and real-world hyperspectral datasets unequivocally demonstrate that our approach outperforms other state-of-the-art approaches in terms of both quantitative and qualitative evaluations. Our code is publicly available at https://github.com/YoungP2001/DBSR.

Deep self-supervised spatial-variant image deblurring

Most existing model-based and learning-based image deblurring methods usually use synthetic blur-sharp training pairs to remove blur. However, these approaches do not perform well in real-world applications as the blur-sharp training pairs are difficult to be obtained and the blur in real-world scenarios is spatial-variant. In this paper, we propose a self-supervised learning-based image deblurring method that can deal with both uniform and spatial-variant blur distributions. Moreover, our method does not need for blur-sharp pairs for training. In our proposed method, we design the Deblurring Network (D-Net) and the Spatial Degradation Network (SD-Net). Specifically, the D-Net is designed for image deblurring while the SD-Net is used to simulate the spatial-variant degradation. Furthermore, the off-the-shelf pre-trained model is employed as the prior of our model, which facilitates image deblurring. Meanwhile, we design a recursive optimization strategy to accelerate the convergence of the model. Extensive experiments demonstrate that our proposed model achieves favorable performance against existing image deblurring methods.

ABDGAN: Arbitrary Time Blur Decomposition Using Critic-Guided TripleGAN.

Recent studies have proposed methods for extracting latent sharp frames from a single blurred image. However, these methods still suffer from limitations in restoring satisfactory images. In addition, most existing methods are limited to decomposing a blurred image into sharp frames with a fixed frame rate. To address these problems, we present an Arbitrary Time Blur Decomposition Triple Generative Adversarial Network (ABDGAN) that restores sharp frames with flexible frame rates. Our framework plays a min-max game consisting of a generator, a discriminator, and a time-code predictor. The generator serves as a time-conditional deblurring network, while the discriminator and the label predictor provide feedback to the generator on producing realistic and sharp image depending on given time code. To provide adequate feedback for the generator, we propose a critic-guided (CG) loss by collaboration of the discriminator and time-code predictor. We also propose a pairwise order-consistency (POC) loss to ensure that each pixel in a predicted image consistently corresponds to the same ground-truth frame. Extensive experiments show that our method outperforms previously reported methods in both qualitative and quantitative evaluations. Compared to the best competitor, the proposed ABDGAN improves PSNR, SSIM, and LPIPS on the GoPro test set by 16.67%, 9.16%, and 36.61%, respectively. For the B-Aist++ test set, our method shows improvements of 6.99%, 2.38%, and 17.05% in PSNR, SSIM, and LPIPS, respectively, compared to the best competitive method.

EFE-CNA Net: An Approach for Effective Image Deblurring Using an Edge-Sensitive Focusing Encoder

Deep learning-based image deblurring techniques have made great advancements, improving both processing speed and deblurring efficacy. However, existing methods still face challenges when dealing with complex blur types and the semantic understanding of images. The segment anything model (SAM), a versatile deep learning model that accurately and efficiently segments objects in images, facilitates various tasks in computer vision. This article leverages SAM’s proficiency in capturing object edges and enhancing image content comprehension to improve image deblurring. We introduce the edge-sensitive focusing encoder (EFE) module, which utilizes masks generated by the SAM framework and re-weights the masked portion following SAM segmentation by detecting its features and high-frequency information. The EFE module uses the masks to locate the position of the blur in an image while identifying the intensity of the blur, allowing the model to focus more accurately on specific features. Masks with greater high-frequency information are assigned higher weights, prompting the network to prioritize them during processing. Based on the EFE module, we develop a deblurring network called the edge-sensitive focusing encoder-based convolution–normalization and attention network (EFE-CNA Net), which utilizes the EFE module to enhance the deblurring process, employs an image-mask decoder to merge features from both the image and the mask from the EFE module, and incorporates the CNA Net as its base network. This design enables the model to focus on distinct features at various locations, enhancing its learning process through the guidance provided by the EFE module and the blurred images. Testing results on the RealBlur and REDS datasets demonstrate the effectiveness of the EFE-CNA Net, achieving peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) metrics of 28.77, 0.902 (RealBlur-J), 36.40, 0.956 (RealBlur-R), 31.45, and 0.919 (REDS).

Deep learning-based restoration of nonlinear motion blurred images for plant classification using multi-spectral images

There have been various plant image-based studies for segmentation, deblurring, super-resolution reconstruction, and classification. However, nonlinear motion blur in thermal images was not considered in the existing studies on plant classification. Nonlinear motion blur occurs in images due to camera or plant movements, and it causes the degradation of plant classification accuracy. Moreover, nonlinear motion blur in images gets worse when both camera and plant movements occur simultaneously. In this case, it becomes difficult to recognize plants, and the performance of plant image classification becomes very low. Therefore, to reduce the nonlinear motion blur, a thermal and visible light plant images-based deblurring network (TVPD-Net) is proposed in this study. In addition, a thermal and visible light plant images-based classification network (TVPC-Net) is also proposed to improve the plant classification performance on deblurred images. Experimental results revealed that the proposed TVPD-Net achieved 21.21 and 22.53 of the peak signal-to-noise ratio (PSNR), and 0.726 and 0.737 of the structural similarity index measure (SSIM) on both visible light and thermal plant image datasets which were self-collected, respectively. Moreover, the proposed TVPC-Net with deblurred images by TVPD-Net achieved 92.52 % (top-1 accuracy) and 87.73 % (harmonic mean of precision and recall (F1-score)). In addition, the experimental results on an open dataset named Hyperspectral Flower Dataset (HFD100) revealed that the proposed plant classification method achieved 90.94 % of top-1 accuracy and 86.21 % of F1-score. The accuracies of the proposed methods are greater than those of the state-of-the-art methods.

Deblurring Network for UV Images of Colorless Chemicals Floating on Sea Surface

Automatic imaging monitoring technology has been developed as a mature solution to address oil spill accidents. However, when airborne equipment is used to monitor the area of leakage, there is a chance of relative motion between the equipment and the target, leading to blurred images. This can hinder subsequent monitoring tasks, such as the identification and segmentation of hazardous chemical targets. Therefore, it is crucial to deblur these images, as sharper images can substantially improve the precision and accuracy of these tasks. In light of this, this paper presents a novel multi-scale recurrent deblurring network, leveraging the Convolutional Block Attention Module (CBAM) attention mechanism, to restore clear images in an end-to-end manner. The CBAM attention mechanism has been incorporated, which learns features in both the spatial and channel domains, thereby enhancing the deblurring ability of the network by combining the attention mechanisms of multiple domains. To evaluate the effectiveness of the proposed method, we applied the deblurring network to our self-built dataset of blurred ultraviolet (UV) images of colorless chemicals floating on water surfaces. Compared to the SRN-Deblur deblurring network, the proposed approach yields improved PSNR and SSIM results. Moreover, when compared with the state-of-the-art DeblurGANv2 method, it performs better in the SSIM. These results demonstrate that the proposed multi-scale recurrent deblurring network, based on the CBAM attention mechanism, exhibits a superior deblurring performance.

Improved Transformer-Based Deblurring of Commodity Videos in Dynamic Visual Cabinets

In the dynamic visual cabinet, the occurrence of motion blur when consumers take out commodities will reduce the accuracy of commodity detection. Recently, although Transformer-based video deblurring networks have achieved results compared to Convolutional Neural Networks in some blurring scenarios, they are still challenging for the non-uniform blurring problem that occurs when consumers pick up the commodities, such as the problem of difficult alignment of blurred video frames of small commodities and the problem of underutilizing the effective information between the video frames of commodities. Therefore, an improved Transformer video deblurring network is proposed. Firstly, a multi-scale Transformer feature extraction method is utilized for non-uniform blurring. Secondly, for the problem of difficult alignment of small-item-blurred video frames, a temporal interactive attention mechanism is designed for video frame alignment. Finally, a feature recurrent fusion mechanism is introduced to supplement the effective information of commodity features. The experimental results show that the proposed method has practical significance in improving the accuracy of commodity detection. Moreover, compared with the recent Transformer deblurring algorithm Video Restoration Transformer, the Peak Signal-to-Noise Ratio of this paper’s algorithm is higher than that of the Deep Video Deblurring dataset and the Fuzzy Commodity Dataset by 0.23 dB and 0.81 dB, respectively.

Memory-based gradient-guided progressive propagation network for video deblurring

Memory-based gradient-guided progressive propagation network for video deblurring

CNB Net: A Two-Stage Approach for Effective Image Deblurring

Image blur, often caused by camera shake and object movement, poses a significant challenge in computer vision. Image deblurring strives to restore clarity to these images. Traditional single-stage methods, while effective in detail enhancement, often neglect global context in favor of local information. Yet, both aspects are crucial, especially in real-life scenarios where images are typically large and subject to various blurs. Addressing this, we introduce CNB Net, an innovative deblurring network adept at integrating global and local insights for enhanced image restoration. The network operates in two stages, utilizing our specially designed Convolution and Normalization-Based Block (CNB Block) and Convolution and Normalization-Based Plus Block (CNBP Block) for multi-scale information extraction. A progressive learning approach is adopted with a Feature Active Selection (FAS) module at the end of each stage that captures spatial detail information under the guidance of real images. The Two-Stage Feature Fusion (TSFF) module reduces information loss caused by downsampling operations while enriching features across stages for increased robustness. We conduct experiments on the GoPro dataset and the HIDE dataset. On the GoPro dataset, our Peak Signal-to-Noise Ratio (PSNR) result is 32.21 and the Structural Similarity (SSIM) result is 0.950; and on the HIDE dataset, our PSNR result is 30.38 and the SSIM result is 0.932. Our results exceed other similar algorithms. By comparing the generated feature maps, we find that our model takes into account both global and local information well.

Real‐world image deblurring using data synthesis and feature complementary network

AbstractMany learning‐based approaches to image deblurring have received increasing attention in recent years. However, the models trained on existing synthetic datasets do not generalize well to real‐world blur, resulting in undesirable artifacts and residual blur. This work attempts to address this problem from two aspects: training data synthesis and network architecture. To narrow the domain gap between synthetic and real domains, a realistic blur synthesis pipeline to generate high‐quality blurred data is proposed. Since the blur is non‐uniform and has different scales and degrees, a parallel feature complementary module to fully exploit the local and non‐local information, which improves the feature representation and helps the network to perceive the non‐uniform blur, is developed. In addition, a spatial Fourier reconstruction block to facilitate correct detail recovery in the spatial and Fourier domains is introduced. Based on these two designs, an effective encoder–decoder network for deblurring is designed. Extensive experiments demonstrate the validity and superiority of the proposed blur synthesis method and deblurring network. In particular, the proposed deblurring network can achieve superior or comparable performance to Restormer, while saving 70% of network parameters and 53% of floating point operations (FLOPs).

Self-supervised multi-scale neural network for blind deblurring

Self-supervised multi-scale neural network for blind deblurring

Prior Guided Multiscale Dynamic Deblurring Network for Diffraction Image Restoration in Droplet Measurement

Prior Guided Multiscale Dynamic Deblurring Network for Diffraction Image Restoration in Droplet Measurement

INformer: Inertial-Based Fusion Transformer for Camera Shake Deblurring.

Inertial measurement units (IMU) in the capturing device can record the motion information of the device, with gyroscopes measuring angular velocity and accelerometers measuring acceleration. However, conventional deblurring methods seldom incorporate IMU data, and existing approaches that utilize IMU information often face challenges in fully leveraging this valuable data, resulting in noise issues from the sensors. To address these issues, in this paper, we propose a multi-stage deblurring network named INformer, which combines inertial information with the Transformer architecture. Specifically, we design an IMU-image Attention Fusion (IAF) block to merge motion information derived from inertial measurements with blurry image features at the attention level. Furthermore, we introduce an Inertial-Guided Deformable Attention (IGDA) block for utilizing the motion information features as guidance to adaptively adjust the receptive field, which can further refine the corresponding blur kernel for pixels. Extensive experiments on comprehensive benchmarks demonstrate that our proposed method performs favorably against state-of-the-art deblurring approaches.

A encoder-decoder deblurring network combined with high-frequency a priori

Convolutional neural network based methods have been proposed to address blind deblurring. Aiming at the difficulty of reconstructing high-frequency features of images with existing network models, this paper proposes a two-stage convolution-based encoder-decoder for fusing high-frequency a prior. In the first stage, both blurred and high-frequency images are input, and the image features extracted by the network and the high-frequency features are fused. In the second stage, the fused features are further refined and recovered as potentially clear images, and the reconstruction ability of the model for high-frequency features is enhanced. In addition, this paper proposes a deep feature reorganization module that integrates multi-layer semantic information in the encoder-decoder and targets the encoder semantics to further enhance the feature characterization capability of the model. Comprehensive experimental results show that our method achieves 0.9085 structural similarity index (SSIM) and 30.66db peak signal-to-noise ratio (PSNR) on the GoPro dataset. Meanwhile, our method achieves 0.8514 SSIM and 27.39db PSNR on the Lai dataset.

A Motion Deblurring Network for Enhancing UAV Image Quality in Bridge Inspection

Unmanned aerial vehicles (UAVs) have been increasingly utilized for facility safety inspections due to their superior safety, cost effectiveness, and inspection accuracy compared to traditional manpower-based methods. High-resolution images captured by UAVs directly contribute to identifying and quantifying structural defects on facility exteriors, making image quality a critical factor in achieving accurate results. However, motion blur induced by external factors such as vibration, low light conditions, and wind during UAV operation significantly degrades image quality, leading to inaccurate defect detection and quantification. To address this issue, this research proposes a deblurring network using a Generative Adversarial Network (GAN) to eliminate the motion blur effect in UAV images. The GAN-based motion deblur network represents an image inpainting method that leverages generative models to correct blurry artifacts, thereby generating clear images. Unlike previous studies, this proposed approach incorporates deblur and blur learning modules to realistically generate blur images required for training the generative models. The UAV images processed using the motion deblur network are evaluated using a quality assessment method based on local blur map and other well-known image quality assessment (IQA) metrics. Moreover, in the experiment of crack detection utilizing the object detection system, improved detection results are observed when using enhanced images. Overall, this research contributes to improving the quality and accuracy of facility safety inspections conducted with UAV-based inspections by effectively addressing the challenges associated with motion blur effects in UAV-captured images.

Joint learning of motion deblurring and defocus deblurring networks with a real-world dataset

When recovering the sharp image from a blurry observation, moving objects, e.g., people and vehicles, usually attract more perceptual attention. However, existing motion deblurring methods primarily focus on removing the global camera motion blur, while neglecting the object motion blur. In this paper, we propose a joint learning framework for motion deblurring and defocus deblurring (JLMD), where a motion deblurring network can be trained for removing object motion blur, and a defocus deblurring network can be also obtained as a byproduct. Especially, we propose to circumvent the hardship in obtaining all-sharp ground truth for object motion blurry images by leveraging the complementary nature between object motion blur and defocus blur. The JLMD framework incorporates three key components. Firstly, a mask generation module is deployed to predict the boundary of motion blur. Secondly, a mutual supervision mechanism is elaborated, which enables the defocus blurry image and the motion blurry image to serve as the ground truth for each other. Thirdly, a content preservation loss is designed to encourage non-blurry regions to stay unchanged. Furthermore, we introduce a Defocus and Motion Deblurring Dataset (DMDD), which is the first real-world dataset specifically dedicated to object motion blurry images. Extensive experiments validate that our method is more effective in removing object motion blur than state-of-the-art methods, while it is at least comparable or superior in removing global camera motion blur and defocus blur. The source code and dataset are available at https://github.com/liyucs/JLMD.

Multi-Scale Frequency Separation Network for Image Deblurring

Image deblurring aims to restore the detailed texture information or structures from the blurry images, which has become an indispensable step in many computer vision tasks. Although various methods have been proposed to deal with the image deblurring problem, most of them treated the blurry image as a whole and neglected the characteristics of different image frequencies. In this paper, we present a new method called multi-scale frequency separation network (MSFS-Net) for image deblurring. MSFS-Net introduces the frequency separation module (FSM) into an encoder-decoder network architecture to capture the low- and high-frequency information of image at multiple scales. Then, a simple cycle-consistency strategy and a sophisticated contrastive learning module (CLM) are respectively designed to retain the low-frequency information and recover the high-frequency information during deblurring. At last, the features of different scales are fused by a cross-scale feature fusion module (CSFFM). Extensive experiments on benchmark datasets show that the proposed network achieves state-of-the-art performance.

Locally Adaptive Channel Attention-Based Spatial–Spectral Neural Network for Image Deblurring

Recently, due to the rapid development of deep neural networks in the field of computer vision, many studies have been conducted in the field of image deblurring. However, previous methods cannot attain satisfactory deblurring performance in object boundaries and local regions containing image details in restored results. This paper proposes a new method that uses a locally adaptive channel attention module for a spectral–spatial network to resolve the problem of single-image deblurring. Unlike existing methods, our proposed method consists of a spectral restorer and spatial restorer that adopt a locally adaptive attention mechanism in the spectral–spatial domains. In addition, unlike a conventional spectral–spatial network that only considers the magnitude of the frequency coefficients, the proposed method uses both the magnitude and phase of the frequency coefficients in the training stage. Our locally adaptive channel attention spectral–spatial network can focus on informative channels that are closely related to blur artifacts. Specifically, the spatial restorer, which guides the intensity of the blur image to fit the ground truth by exploring the interdependencies of feature channels, can efficiently restore scene characteristics while the spectral restorer, which guides the magnitude and phase of the blur image’s frequency coefficients to fit those of the ground truth by exploring the interdependencies of feature channels, fine-tunes the details of structures. The experimental results show that the proposed method outperformed the deblurring results compared to benchmark methods in terms of both qualitative evaluation and quantitative metrics.

Deep coded exposure: end-to-end co-optimization of flutter shutter and deblurring processing for general motion blur removal

Coded exposure photography is a promising computational imaging technique capable of addressing motion blur much better than using a conventional camera, via tailoring invertible blur kernels. However, existing methods suffer from restrictive assumptions, complicated preprocessing, and inferior performance. To address these issues, we proposed an end-to-end framework to handle general motion blurs with a unified deep neural network, and optimize the shutter’s encoding pattern together with the deblurring processing to achieve high-quality sharp images. The framework incorporates a learnable flutter shutter sequence to capture coded exposure snapshots and a learning-based deblurring network to restore the sharp images from the blurry inputs. By co-optimizing the encoding and the deblurring modules jointly, our approach avoids exhaustively searching for encoding sequences and achieves an optimal overall deblurring performance. Compared with existing coded exposure based motion deblurring methods, the proposed framework eliminates tedious preprocessing steps such as foreground segmentation and blur kernel estimation, and extends coded exposure deblurring to more general blind and nonuniform cases. Both simulation and real-data experiments demonstrate the superior performance and flexibility of the proposed method.