Application of Deep Learning-Based Methods to the Single Image Non-Uniform Blind Motion Deblurring Problem

In this paper, we present deep learning-based blind image deblurring methods for estimating and removing a non-uniform motion blur from a single blurry image. We propose two fully convolutional neural networks (CNN) for solving the problem. The networks are trained end-to-end to reconstruct the latent sharp image directly from the given single blurry image without estimating and making any assumptions on the blur kernel, its uniformity, and noise. We demonstrate the performance of the proposed models and show that our approaches can effectively estimate and remove complex non-uniform motion blur from a single blurry image.

Download Full-text

Non-blind Image Deblurring from a Single Image

Cognitive Computation ◽

10.1007/s12559-012-9139-2 ◽

2012 ◽

Vol 5 (1) ◽

pp. 3-12 ◽

Cited By ~ 3

Author(s):

Bo Zhao ◽

Wensheng Zhang ◽

Huan Ding ◽

Hu Wang

Keyword(s):

Image Deblurring ◽

Single Image ◽

Blind Image Deblurring ◽

Blind Image

Download Full-text

SlimDeblurGAN-Based Motion Deblurring and Marker Detection for Autonomous Drone Landing

Sensors ◽

10.3390/s20143918 ◽

2020 ◽

Vol 20 (14) ◽

pp. 3918

Author(s):

Noi Quang Truong ◽

Young Won Lee ◽

Muhammad Owais ◽

Dat Tien Nguyen ◽

Ganbayar Batchuluun ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Processing Time ◽

Detection Method ◽

Uniform Motion ◽

Two Phase ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Motion Deblurring ◽

Marker Detection

Deep learning-based marker detection for autonomous drone landing is widely studied, due to its superior detection performance. However, no study was reported to address non-uniform motion-blurred input images, and most of the previous handcrafted and deep learning-based methods failed to operate with these challenging inputs. To solve this problem, we propose a deep learning-based marker detection method for autonomous drone landing, by (1) introducing a two-phase framework of deblurring and object detection, by adopting a slimmed version of deblur generative adversarial network (DeblurGAN) model and a You only look once version 2 (YOLOv2) detector, respectively, and (2) considering the balance between the processing time and accuracy of the system. To this end, we propose a channel-pruning framework for slimming the DeblurGAN model called SlimDeblurGAN, without significant accuracy degradation. The experimental results on the two datasets showed that our proposed method exhibited higher performance and greater robustness than the previous methods, in both deburring and marker detection.

Download Full-text

Gradient-wise search strategy for blind image deblurring

MATEC Web of Conferences ◽

10.1051/matecconf/202235503005 ◽

2022 ◽

Vol 355 ◽

pp. 03005

Author(s):

Yunhong Wang ◽

Dan Liu

Keyword(s):

Iterative Methods ◽

Conjugate Gradient Method ◽

Conjugate Gradient ◽

Gradient Method ◽

Search Strategy ◽

Image Deblurring ◽

Motion Blur ◽

Step Size ◽

Blind Image Deblurring ◽

Blind Image

Blind image deblurring is a long-standing challenging problem to improve the sharpness of an image as a prerequisite step. Many iterative methods are widely used for the deblurring image, but care must be taken to ensure that the methods have fast convergence and accuracy solutions. To address these problems, we propose a gradient-wise step size search strategy for iterative methods to achieve robustness and accelerate the deblurring process. We further modify the conjugate gradient method with the proposed strategy to solve the bling image deblurring problem. The gradient-wise step size aims to update gradient for each pixel individually, instead of updating step size by the fixed factor. The modified conjugate gradient method improves the convergence performance computation speed with a gradient-wise step size. Experimental results show that our method effectively estimates the sharp image for both motion blur images and defocused images. The results of synthetic datasets and natural images are better than what is achieved with other state-of-the-art blind image deblurring methods.

Download Full-text

Variational-EM-Based Deep Learning for Noise-Blind Image Deblurring

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) ◽

10.1109/cvpr42600.2020.00368 ◽

2020 ◽

Cited By ~ 1

Author(s):

Yuesong Nan ◽

Yuhui Quan ◽

Hui Ji

Keyword(s):

Deep Learning ◽

Image Deblurring ◽

Blind Image Deblurring ◽

Variational Em ◽

Blind Image

Download Full-text

Dual Image Deblurring Using Deep Image Prior

Electronics ◽

10.3390/electronics10172045 ◽

2021 ◽

Vol 10 (17) ◽

pp. 2045

Author(s):

Chang Jong Shin ◽

Tae Bok Lee ◽

Yong Seok Heo

Keyword(s):

Image Deblurring ◽

Superior Performance ◽

Natural Image ◽

Blind Image Deblurring ◽

Image Prior ◽

Ill Posed ◽

Deep Image ◽

Sharp Image ◽

Blurred Images ◽

Blind Image

Blind image deblurring, one of the main problems in image restoration, is a challenging, ill-posed problem. Hence, it is important to design a prior to solve it. Recently, deep image prior (DIP) has shown that convolutional neural networks (CNNs) can be a powerful prior for a single natural image. Previous DIP-based deblurring methods exploited CNNs as a prior when solving the blind deburring problem and performed remarkably well. However, these methods do not completely utilize the given multiple blurry images, and have limitations of performance for severely blurred images. This is because their architectures are strictly designed to utilize a single image. In this paper, we propose a method called DualDeblur, which uses dual blurry images to generate a single sharp image. DualDeblur jointly utilizes the complementary information of multiple blurry images to capture image statistics for a single sharp image. Additionally, we propose an adaptive L2_SSIM loss that enhances both pixel accuracy and structural properties. Extensive experiments show the superior performance of our method to previous methods in both qualitative and quantitative evaluations.

Download Full-text

Sparsity and Smoothing Multi-Regularization Constraints for Blind Image Deblurring

Journal of Software ◽

10.3724/sp.j.1001.2013.04256 ◽

2013 ◽

Vol 24 (5) ◽

pp. 1143-1154 ◽

Cited By ~ 1

Author(s):

Shu TANG ◽

Wei-Guo GONG ◽

Jian-Hua ZHONG

Keyword(s):

Image Deblurring ◽

Blind Image Deblurring ◽

Blind Image

Download Full-text

Blind Deblurring Based on Sigmoid Function

Sensors ◽

10.3390/s21103484 ◽

2021 ◽

Vol 21 (10) ◽

pp. 3484

Author(s):

Shuhan Sun ◽

Lizhen Duan ◽

Zhiyong Xu ◽

Jianlin Zhang

Keyword(s):

Performance Optimization ◽

Degradation Process ◽

Image Deconvolution ◽

Sigmoid Function ◽

Blind Image Deblurring ◽

Linear Estimators ◽

Blind Deblurring ◽

Degraded Image ◽

Excellent Property ◽

Blind Image

Blind image deblurring, also known as blind image deconvolution, is a long-standing challenge in the field of image processing and low-level vision. To restore a clear version of a severely degraded image, this paper proposes a blind deblurring algorithm based on the sigmoid function, which constructs novel blind deblurring estimators for both the original image and the degradation process by exploring the excellent property of sigmoid function and considering image derivative constraints. Owing to these symmetric and non-linear estimators of low computation complexity, high-quality images can be obtained by the algorithm. The algorithm is also extended to image sequences. The sigmoid function enables the proposed algorithm to achieve state-of-the-art performance in various scenarios, including natural, text, face, and low-illumination images. Furthermore, the method can be extended naturally to non-uniform deblurring. Quantitative and qualitative experimental evaluations indicate that the algorithm can remove the blur effect and improve the image quality of actual and simulated images. Finally, the use of sigmoid function provides a new approach to algorithm performance optimization in the field of image restoration.

Download Full-text

Real-Time Environment Monitoring Using a Lightweight Image Super-Resolution Network

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18115890 ◽

2021 ◽

Vol 18 (11) ◽

pp. 5890

Author(s):

Qiang Yu ◽

Feiqiang Liu ◽

Long Xiao ◽

Zitao Liu ◽

Xiaomin Yang

Keyword(s):

Deep Learning ◽

Real Time ◽

Super Resolution ◽

Model Complexity ◽

Practical Application ◽

Single Image ◽

Feature Maps ◽

Benchmark Datasets ◽

Image Super Resolution ◽

Single Image Super Resolution

Deep-learning (DL)-based methods are of growing importance in the field of single image super-resolution (SISR). The practical application of these DL-based models is a remaining problem due to the requirement of heavy computation and huge storage resources. The powerful feature maps of hidden layers in convolutional neural networks (CNN) help the model learn useful information. However, there exists redundancy among feature maps, which can be further exploited. To address these issues, this paper proposes a lightweight efficient feature generating network (EFGN) for SISR by constructing the efficient feature generating block (EFGB). Specifically, the EFGB can conduct plain operations on the original features to produce more feature maps with parameters slightly increasing. With the help of these extra feature maps, the network can extract more useful information from low resolution (LR) images to reconstruct the desired high resolution (HR) images. Experiments conducted on the benchmark datasets demonstrate that the proposed EFGN can outperform other deep-learning based methods in most cases and possess relatively lower model complexity. Additionally, the running time measurement indicates the feasibility of real-time monitoring.

Download Full-text