Perceiving and Modeling Density for Image Dehazing

Tian, Ye; Zhang, Yuncheng; Jiang, Mingchao; Chen, Liang; Liu, Yun; Chen, Sixiang; Chen, Erkang

doi:10.1007/978-3-031-19800-7_8

Cited by 48 publications

(29 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reference FADE ↓ NIQE ↓ Aligned (i.e., need GT) MSBDN [12] 1.3952 4.5269 CVPR'20 FFANet [43] 2.0734 4.9281 AAAI'20 UHD [69] 1.2457 4.4244 CVPR'21 IPUDN [24] 0.9126 7.3470 Arxiv'22 PMNet [61] 1.4211 4.7523 ECCV'22 DeHamer [17] 1.3062 7.2924 CVPR '22 Non-aligned NSDNet (Ours) 0.7419 3.6905 -Table S6: Comparison of the proposed method and methods with aligned ground truth on RTTS dataset.…”

Section: Data Setting Methodsmentioning

confidence: 99%

“…Part of these GAN variants mainly utilize multi-scale and attention mechanisme(e.g., channel attention, spatial attention) to efficiently extract hazy features, such as [44,43]. Besides, similar network architecture design ideas have also appeared in CNN-based dehazing networks [26,64,46,11,34,12,61]. Recently, visual transformers (ViT) is used to design different structures for improving dehazing performance [66,51,53,17].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Non-aligned supervision for Real Image Dehazing

Fan¹,

Guo²,

Qian³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Data Setting Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Non-aligned supervision for Real Image Dehazing

Fan¹,

Guo²,

Qian³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…ITS contains 13, 990 indoor pair images and the indoor set of the SOTS dataset includes 500 indoor pair images. For the Haze4K dataset, we follow the previous work [68]. The Haze4K dataset contains 3, 000 haze and haze-free image pairs for training and 1, 000 for testing.…”

Section: Methodsmentioning

confidence: 99%

Deep Residual Haze Network for Image Dehazing and Deraining

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Image dehazing on a hazy image aims to remove the haze and make the image scene clear, which attracts more and more research interests in recent years. Most existing image dehazing methods use a classic atmospheric scattering model and natural image priors to remove the image haze. In this paper, we propose an end-to-end image dehazing model termed as DRHNet (Deep Residual Haze Network), which restores the haze-free image by subtracting the learned negative residual map from the hazy image. Specifically, DRHNet proposes a context-aware feature extraction module to aggregate the contextual information effectively. Furthermore, it proposes a novel nonlinear activation function termed as RPReLU (Reverse Parametric Rectified Linear Unit) to improve its representation ability and to accelerate its convergence. Extensive experiments demonstrate that DRHNet outperforms state-of-the-art methods both quantitatively and qualitatively. In addition, experiments on image deraining task show that DRHNet can also serve for image deraining. INDEX TERMS Image dehazing, image deraining, negative residual map, context-aware feature extraction, reverse parametric rectified linear unit (RPReLU).

show abstract

“…Underwater imaging plays a significant role in underwater robotics [1], providing essential information for perceiving and understanding underwater environments. Recently, more and more works [2][3][4][5][6] have paid attention to realw-world image restoration problems with challenging degradations. According to the Jaffe-McGlamey imaging model [7,8], underwater imaging consists of a linear superposition of direct, back scattered, and forward scattered components.…”

Section: Introductionmentioning

confidence: 99%

RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement

Jiang¹,

Bai²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles. To address this issue, we propose a Real-time Spatial and Frequency Domains Modulation Network (RSFDM-Net) for the efficient enhancement of colors and details in underwater images. Specifically, our proposed conditional network is designed with Adaptive Fourier Gating Mechanism (AFGM) and Multiscale Convolutional Attention Module (MCAM) to generate vectors carrying low-frequency background information and highfrequency detail features, which effectively promote the network to model global background information and local texture details. To more precisely correct the color cast and low saturation of the image, we introduce a Three-branch Feature Extraction (TFE) block in the primary net that processes images pixel by pixel to integrate the color information extended by the same channel (R, G, or B). This block consists of three small branches, each of which has its own weights. Extensive experiments demonstrate that our network significantly outperforms over state-of-the-art methods in both visual quality and quantitative metrics.

show abstract

Perceiving and Modeling Density for Image Dehazing

Cited by 48 publications

References 20 publications

Non-aligned supervision for Real Image Dehazing

Non-aligned supervision for Real Image Dehazing

Deep Residual Haze Network for Image Dehazing and Deraining

RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement

Contact Info

Product

Resources

About