A novel dynamic scene deblurring framework based on hybrid activation and edge-assisted dual-branch residuals

Li, Zihan; Cui, Guangmang; Liu, Haoyu; Chen, Ziyi; Zhao, Jufeng

doi:10.1007/s00371-024-03390-7

Cited by 1 publication

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have highlighted the effectiveness of segmentation-assist deblurring methods [1][2][3][4]. Krishnan et al [1] proposed a blind image deblurring method using normalized sparsity measures, segmenting the image into distinct regions to infer the blur kernel and clear image based on regional sparsity.…”

Section: Introductionmentioning

confidence: 99%

“…Zhang et al [3] introduced a method using a three-stage intensity prior, enhancing deblurring by modeling intensity distributions in three distinct regions. Li et al [4] introduced a dynamic scene deblurring framework that employs hybrid activation functions and edge-assisted dual-branch residuals. This method enhances deblurring performance by leveraging a combination of activation functions to capture diverse image features and incorporating edge information to guide the deblurring process through a dual-branch architecture, which separately processes edge details and broader image structures.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Zheng,

Zhang,

Jiang

et al. 2024

Electronics

View full text Add to dashboard Cite

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).

show abstract