A Lightweight Channel-spatial Attention Network for Real-time Image De-raining

Zeng, Yirui; Ma, Zhengming

doi:10.1145/3379299.3379305

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing image denoising methods can be broadly categorized into four types: The first is filter-based methods [1] , which employ filters such as mean, median, and Gaussian filters to smooth the image and remove noise. The second type involves frequency domain-based techniques [2] , where the image is transformed into the frequency domain for noise modeling and removal, commonly using Fast Fourier Transform (FFT) and wavelet transform. The third approach is image restorationbased methods [3] , utilizing algorithms like image interpolation and inpainting to restore noise-contaminated regions.…”

Section: Introductionmentioning

confidence: 99%

An all-in-one lightweight image restoration network based on polarized attention mechanism and efficient feature extraction

Zhang,

Yuan

2024

International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023)

View full text Add to dashboard Cite

Removing noise from images is a challenging task in front-end computer vision applications, especially in snowy, rainy, foggy, and underwater environments, which pose significant difficulties for various visual tasks. Existing image restoration methods often struggle to achieve robust generalization and are burdened with immense computational complexity. This paper introduces a lightweight image restoration network based on polarized attention mechanisms and efficient feature extraction, capable of addressing tasks like rain removal, snow removal, fog removal, and underwater image enhancement. Initially, a polarized self-attention mechanism is proposed to intricately learn weather noise, followed by an efficient noise removal module complementing the initial network. This addition compensates for any noise information overlooked by the polarized self-attention mechanism. Furthermore, residual connections are integrated into each module of the network, along with grouped convolutions, to prevent network degradation and reduce computational load. In comparison to existing models, this network not only learns noise with similar shapes but also adapts to noise with significant shape variations. Additionally, the introduced residual structure ensures the network's stability, avoiding performance degradation before achieving expected results. The collaborative use of the efficient noise removal module and polarized self-attention mechanism sets a high standard for noise learning in this network. Experimental results demonstrate the efficacy of this algorithm on publicly available datasets including Snow100K, CSD, Rain200H, Rain200L, Rain800, RSID, and EUVP. The proposed method efficiently removes various image noises, effectively achieving the desired image restoration objectives.

show abstract

Section: Introductionmentioning

confidence: 99%

An all-in-one lightweight image restoration network based on polarized attention mechanism and efficient feature extraction

Zhang,

Yuan

2024

International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023)

View full text Add to dashboard Cite

show abstract

“…In recent years, deep learning-based methods are very popular. Zeng et al [27]proposed a lightweight channel spatial attention network for real-time image de-raining. YU et al [26]proposed a progressive network for single-image rain removal.…”

Section: Abstract Rain Removal • Rotation Operator • Low Rank 1 Intro...mentioning

confidence: 99%

RoDeRain: Rotational Video Derain via Nonconvex and Nonsmooth Optimization

Deng

Zhu

2021

Mobile Netw Appl

View full text Add to dashboard Cite

Video derain is an important issue in the field of digital image processing and computer vision. This paper divides rain streaks into two types: one is rain in natural scenes, and the other is rain in stochastic scenes. In this paper, we propose a novel rotational video derain algorithm via nonconvex and nonsmooth algorithm (RoDerain). Not only can the rain streaks in natural scene be removed, but the rain streaks in stochastic scene can be also well removed. This paper added the rotation operator based on the discriminatively intrinsic priors of rain streaks and clean videos to remove the rain streaks in both natural and stochastic scenes.For the low rank problem of the background, we replace the solution of the nuclear norm with improved IRNN-Capped L 1 suitable for tensor. Finally,this paper used the Alternating Direction Method of Multipliers (ADMM) to optimize the solution of the proposed rain streaks removal algorithm model.The disadvantage is that global information is not considered. And the extensive experiment results show that our proposed algorithm performs favorably in comparison to several popular rain removal algorithms.

show abstract