Abstract
Non-uniform blind deblurring of dynamic scenes has always been a challenging problem in image processing because of the diverse of blurring sources. Traditional methods based on energy minimization cannot make accurate kernel estimation. It leads to that some high frequency details cannot be fully recovered. Recently, many methods based on convolution neural networks (CNNs) have been proposed to improve the overall performance. Followed by this trend, we first propose a two-stage deblurring module to recover the blur images of dynamic scenes based on high frequency residual image learning. The first stage performs initial deburring with the blur kernel estimated by the salient structure. The second stage calculates the difference of input image and initially deblurred image, referred to as residual image, and adopt an encoder-decoder network to refine the residual image. Finally, we can combine the refined residual image with the input blurred image to obtain the latent image. To increase deblurring performance, we further propose a coarse-to-fine framework based on the deblurring module. It performs the deblurring module many times in a multi-scale manner which can gradually restore the sharp edge details of different scales. Experiments conducted on three benchmark datasets demonstrate the proposed method achieves competitive performance of state-of-art methods.
Highlights
Blind image deblurring (BID) has been received much attention and made a significant progress in the recent years [1]–[38]
We propose a novel concept for deblurring, which separates deblurring into low-frequency content recovery and high frequency information refinement
Nah et al [25] proposed an end-to-end convolutional neural network for real motion blur which combined with coarse-to-fine strategy, and [26], [27] proposed an end-to-end architecture constructed by generative adversarial network
Summary
Blind image deblurring (BID) has been received much attention and made a significant progress in the recent years [1]–[38]. Liu et al.: Motion Deblur Method Based on Multi-Scale High Frequency Residual Image Learning containing non-uniform blurring components. Later, [23]–[28] proposed other CNN-based methods which restore sharp images directly without estimating the blur kernel in advance. They integrate encoder and decoder networks into a single framework, and adopt end-to-end training strategy to make deblurring task simpler. It is allowed to use relatively smaller amount of training samples Inspired by this idea, this paper proposes a multiscale deblurring method based on residual image learning. The first stage performs initial deblurring with the blur kernel estimated by the salient structure of the input image.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
