A Motion Deblur Method Based on Multi-Scale High Frequency Residual Image Learning

Liu, Keng Hao; Yeh, Chia Hung; Chung, Juh Wei; Chang, Chuan Yu

doi:10.1109/access.2020.2985220

Cited by 28 publications

(26 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al. [55] employ a two‐stage module to deblur images. The first stage is based on statistical parameter estimation, while the second stage is based on deep neural network restoration to remove artifacts and retain the shape of an image.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

“…Likewise, Wei et al [96] propose a neural network with local correlation blocks to deblur dynamic scene blurred images. Liu et al [55] employ a two-stage module to deblur images. The first stage is based on statistical parameter estimation, while the second stage is based on deep neural network restoration to remove artifacts and retain the shape of an image.…”

Section: Deep Learning-based Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Khan

Luo

2022

IET Image Processing

View full text Add to dashboard Cite

Processing images with heterogeneous blur remains challenging due to multiple degradation aspects that could affect structural properties. This study proposes a deep learning‐based multi‐scaled generative adversarial network (GAN) with residual image learning to process variant and in‐variant blur. Different scaled images with corresponding gradients are concatenated as a multi‐channel single input for the proposed GAN. Residual‐ and dense‐networks are combined to explore salient features in the bottleneck section while addressing the vanishing gradient problem. A hybrid content loss function with a gradient penalty minimises the error between generated and ground truth images. Due to structure sparsity, the generated output may lose some information that leads to artifacts. Residual image learning with dilation and end‐to‐end training is used to resolve this issue by recovering high‐resolution anatomical details. Three different datasets: GoPro, Köhler, and Lai, with variant and in‐variant blur, are used to perform qualitative and quantitative analyses. Experiments show the proposed method is effective in reducing blur while preserving structural properties compared to multiple preprocessing techniques for image analysis. Moreover, the consistently improved performance over multiple publicly available datasets validates the merits of the proposed method for large data analysis.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

Section: Deep Learning-based Techniquesmentioning

confidence: 99%

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Khan

Luo

2022

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…These methods combine the CNNs and maximum a posteriori probability (MAP)based algorithms. On the other hand, several CNN models directly restore the sharp image from blurred image in an end-to-end manner [24]- [29]. Nah et al [24] proposed a multi-scale CNN model.…”

Section: A Generic Image Deblurringmentioning

confidence: 99%

Progressive Semantic Face Deblurring

2020

View full text Add to dashboard Cite

Previous face deblurring methods have utilized semantic segmentation maps as prior knowledge. Most of these methods generated the segmentation map from a blurred facial image, and restore it using the map in a sequential manner. However, the accuracy of the segmentation affects the restoration performance. Generally, it is difficult to obtain an accurate segmentation map from a blurred image. Instead of sequential methods, we propose an efficient method that learns the flows of facial component restoration without performing segmentation. To this end, we propose a multi-semantic progressive learning (MSPL) framework that progressively restores the entire face image starting from the facial components such as the skin, followed by the hair, and the inner parts (eyes, nose, and mouth). Furthermore, we propose a discriminator that observes the reconstruction-flow of the generator. In addition, we present new test datasets to facilitate the comparison of face deblurring methods. Various experiments demonstrate that the proposed MSPL framework achieves higher performance in facial image deblurring compared to the existing methods, both qualitatively and quantitatively. Our code, trained model and data are available at https://github.com/dolphin0104/MSPL-GAN. INDEX TERMS Facial image deblurring, semantic mask, progressive learning, generative adversarial network, deep learning

show abstract

“…Moreover, the ConvLSTM module can be used to aggregate feature maps from coarse-to-fine scales. Liu et al [14] proposed a two-stage deblurring module to recover the blur images of dynamic scenes based on high-frequency residual image learning. EH-GAN [15] propose an edge heuristic multiscale generative adversarial network (GANs) [5], which uses the coarse-to-fine scheme to restore clear images in an endto-end manner.…”

Section: Related Workmentioning

confidence: 99%

Semantic Information Supplementary Pyramid Network for Dynamic Scene Deblurring

et al. 2020

View full text Add to dashboard Cite

The algorithm in this paper is called semantic information supplementary pyramid network(SIS-net). We choose Generative Adversarial Network (GAN) as its fundamental model. SIS-net's generator imitates the feature pyramid network (FPN) structure to recycle features spanning across multiple receptive scales to restore a sharp image. However, to solve the problem caused by the phenomenon of semantic dilution in the FPN network, we have innovatively designed a semantic information supplement(SIS) mechanism. SIS mechanism contains two essential components: semantic information storage box (info-box) and feature fusion expanding. In the process of feature fusion expanding, the semantic information features coming from the info-box is supplemented to make greater use of detailed clues. In addition, SIS-net uses the intermediate layer path to extract image features in a single time to obtain a multi-scale effect. The running speed of SIS-net has obvious advantages over other algorithms, and can basically complete real-time deblurring tasks. Extensive experiments show that our SIS-net achieves both qualitative and quantitative improvements against state-of-the-art methods.

show abstract

A Motion Deblur Method Based on Multi-Scale High Frequency Residual Image Learning

Cited by 28 publications

References 45 publications

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Multi‐scale GAN with residual image learning for removing heterogeneous blur

Progressive Semantic Face Deblurring

Semantic Information Supplementary Pyramid Network for Dynamic Scene Deblurring

Contact Info

Product

Resources

About