Lightweight Multi-scale Attentional Network for Single Image Dehazing

Zong, Ping; Li, Jinjiang; Hua, Zhen

doi:10.1109/icicml57342.2022.10009715

Cited by 2 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu [ 22 ] and others introduced a feature fusion network with an attention mechanism, which can more flexibly handle problems by fusing different types of information. Ping et al [ 23 ] combined high-level semantics and low-level semantics in feature maps of different scales, also increasing attention to different haze concentration areas. Li et al [ 24 ] proposed a network incorporating fog transmission and feature aggregation, which transfers fog information from real foggy images to clear images, generates training samples to address domain shift issues, and improves the scalability of the dehazing model through feature aggregation.…”

Section: Related Workmentioning

confidence: 99%

Depth-Guided Bilateral Grid Feature Fusion Network for Dehazing

Li,

Qiao,

Wan

et al. 2024

Sensors

View full text Add to dashboard Cite

In adverse foggy weather conditions, images captured are adversely affected by natural environmental factors, resulting in reduced image contrast and diminished visibility. Traditional image dehazing methods typically rely on prior knowledge, but their efficacy diminishes in practical, complex environments. Deep learning methods have shown promise in single-image dehazing tasks, but often struggle to fully leverage depth and edge information, leading to blurred edges and incomplete dehazing effects. To address these challenges, this paper proposes a deep-guided bilateral grid feature fusion dehazing network. This network extracts depth information through a dedicated module, derives bilateral grid features via Unet, employs depth information to guide the sampling of bilateral grid features, reconstructs features using a dedicated module, and finally estimates dehazed images through two layers of convolutional layers and residual connections with the original images. The experimental results demonstrate the effectiveness of the proposed method on public datasets, successfully removing fog while preserving image details.

show abstract

Section: Related Workmentioning

confidence: 99%

Depth-Guided Bilateral Grid Feature Fusion Network for Dehazing

Li,

Qiao,

Wan

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Considering the potential cumulative error caused via the separate estimation of atmospheric light and the transmission map, IFE-Net unifies atmospheric light and transmission maps as one parameter to directly obtain a clean image. In addition, attention mechanisms have been widely applied in the design of neural networks [19,[33][34][35][36], which can provide additional flexibility in the network. Inspired by these works and considering the different weights of features in different regions, a feature attention mechanism module called attention mechanism (AM) is designed in the network, which processes different types of information more effectively.…”

Section: Introductionmentioning

confidence: 99%

IFE-Net: An Integrated Feature Extraction Network for Single-Image Dehazing

Leng,

Liu

2023

Applied Sciences

View full text Add to dashboard Cite

In recent years, numerous single-image dehazing algorithms have made significant progress; however, dehazing still presents a challenge, particularly in complex real-world scenarios. In fact, single-image dehazing is an inherently ill-posed problem, as scene transmission relies on unknown and nonhomogeneous depth information. This study proposes a novel end-to-end single-image dehazing method called the Integrated Feature Extraction Network (IFE-Net). Instead of estimating the transmission matrix and atmospheric light separately, IFE-Net directly generates the clean image using a lightweight CNN. During the dehazing process, texture details are often lost. To address this issue, an attention mechanism module is introduced in IFE-Net to handle different information impartially. Additionally, a new nonlinear activation function is proposed in IFE-Net, known as a bilateral constrained rectifier linear unit (BCReLU). Extensive experiments were conducted to evaluate the performance of IFE-Net. The results demonstrate that IFE-Net outperforms other single-image haze removal algorithms in terms of both PSNR and SSIM. In the SOTS dataset, IFE-Net achieves a PSNR value of 24.63 and an SSIM value of 0.905. In the ITS dataset, the PSNR value is 25.62, and the SSIM value reaches 0.925. The quantitative results of the synthesized images are either superior to or comparable with those obtained via other advanced algorithms. Moreover, IFE-Net also exhibits significant subjective visual quality advantages.

show abstract

Lightweight Multi-scale Attentional Network for Single Image Dehazing

Cited by 2 publications

References 15 publications

Depth-Guided Bilateral Grid Feature Fusion Network for Dehazing

Depth-Guided Bilateral Grid Feature Fusion Network for Dehazing

IFE-Net: An Integrated Feature Extraction Network for Single-Image Dehazing

Contact Info

Product

Resources

About