GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing

By Xiaohong Liu, Yongrui Ma, Zhihao Shi. IEEE International Conference on Computer Vision, 2019

1,070 citations recorded by the source corpus.

We propose an end-to-end trainable Convolutional Neural Network (CNN), named GridDehazeNet, for single image dehazing. The GridDehazeNet consists of three modules: pre-processing, backbone, and post-processing. The trainable pre-processing module can generate learned inputs with better diversity and more pertinent features as compared to those derived inputs produced by hand-selected pre-processing methods. The backbone module implements a novel attention-based multi-scale estimation on a grid network, which can effectively alleviate the bottleneck issue often encountered in the conventional multi-scale approach. The post-processing module helps to reduce the artifacts in the final output. Experimental results indicate that the GridDehazeNet outperforms the state-of-the-arts on both synthetic and real-world images. The proposed hazing method does not rely on the atmosphere scattering model, and we provide an explanation as to why it is not necessarily beneficial to take advantage of the dimension reduction offered by the atmosphere scattering model for image dehazing, even if only the dehazing results on synthetic images are concerned.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/56ac346b77730828f5fc3ee3cf1f47d62a1d3343

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (2020, background): “Although it is well-known that multi-resolution fusion is helpful to boosting image recovery performance [7, 12, 44, 23], it is difficult to obtain an effective architecture and almost all existing works rely on human design.”
Image Dehazing Transformer with Transmission-Aware 3D Position Embedding (2022, methodology): “(a) input (b) DCP [14] (c) DehazeNet [4] (d) AODNe [17] (e) GridDehazeNet [20]”
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, methodology): “[18] GDN [10] DuRN?”
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images (2020, methodology): “[28] are limited to restore the contrast in the hazy regions mostly due to their strategy that assume homogeneous hazy scenes.”
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions (2021, neutral): “Another approach is to dilute the inﬂuence of weather-speciﬁc information by preprocessing the image with existing methods such as image defogging (Hang et al. 2020; Liu et al. 2019) and image enhancement (Guo et al. 2020).”
DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention (2023, methodology): “(a) Hazy (b) DCP [12] (c) GDN [24] (d) FFA [5] (e) AECR-Net [6] (f) Dehamer [17] (g) Ours”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, neutral): “GridDehazeNet [10].”
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization (2021, background): “Attention mechanism The pioneer work [56] proposes an attention mechanism to improve the feature representation with relatively low cost, which has been widely employed in various vision tasks [12, 19, 21, 24, 25, 38, 58].”
You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network (2020, methodology): “In recent, motivated by the success of neural networks, some studies (Cai et al. 2016; Ren et al. 2016; Zhu et al. 2018; Li et al. 2017; Liu et al. 2019; Qu et al. 2019; Ancuti et al. 2018a; Mei et al. 2018) have been conducted to apply neural networks to image dehazing, which have achieved the stat”
Vision Transformers for Single Image Dehazing (2022, background): “GridDehazeNet [13] proposes that learning to restore the image is better than estimating t, because the latter will fall into suboptimal solutions.”
MAXIM: Multi-Axis MLP for Image Processing (2022, background): “Visual comparisons for image dehazing on SOTS indoor testset [45] among GCANet [13], GridDehaze [54], DuRN [55], MSBDN [22], FFA-Net [72], and our MAXIM-2S.”
Contrastive Learning for Compact Single Image Dehazing (2021, methodology): “Previous works [35, 30, 34, 23, 10, 42] usually employ the fixed grid kernel (e.”
Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models (2022, background): “There has been an independent line of work focusing solely on image dehazing [1], [49], [50], where also similar GAN based generative solutions were adopted [51].”