Gated Fusion Network for Single Image Dehazing

By Wenqi Ren, Lin Ma, Jiawei Zhang, Jin-shan Pan, Xiaochun Cao, Wei David Liu, Ming-Hsuan Yang. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018

881 citations recorded by the source corpus.

In this paper, we propose an efficient algorithm to directly restore a clear image from a hazy input. The proposed algorithm hinges on an end-to-end trainable neural network that consists of an encoder and a decoder. The encoder is exploited to capture the context of the derived input images, while the decoder is employed to estimate the contribution of each input to the final dehazed result using the learned representations attributed to the encoder. The constructed network adopts a novel fusion-based strategy which derives three inputs from an original hazy image by applying White Balance (WB), Contrast Enhancing (CE), and Gamma Correction (GC). We compute pixel-wise confidence maps based on the appearance differences between these different inputs to blend the information of the derived inputs and preserve the regions with pleasant visibility. The final dehazed image is yielded by gating the important features of the derived inputs. To train the network, we introduce a multi-scale approach such that the halo artifacts can be avoided. Extensive experimental results on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against the state-of-the-art algorithms.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/dbd21420cd1299fdab9a04c6b4b3b5b4d4a38a6d

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

TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions (2021, background): “[43] proposed pre-processing a hazy image to generate multiple inputs thus introducing color distortions to perform dehazing.”
Depth-Attentional Features for Single-Image Rain Removal (2019, background): “, snow [36], raindrops [34, 48], and haze [3, 27, 29, 35, 46, 49].”
PSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors (2021, methodology): “With the advances in deep learning, many methods based on convolutional neural networks (CNNs) [3,4,7,14,22,31, 32] have been proposed to overcome the drawbacks of using physical priors.”
Single Image Dehazing via Multi-scale Convolutional Neural Networks with Holistic Edges (2019, background): “Data-driven dehazing models recently become popular due to the success of machine learning in various vision applications (Ren et al. 2018; Li et al. 2019).”
Human-Aware Motion Deblurring (2019, methodology): “Numerous CNN-based methods have also been applied in an endto-end fashion for image processing and generation problems, such as segmentation [24, 42], super-resolution [53, 22, 14, 15, 44], denoising [25, 49, 59, 47, 48], dehazing and deraining [32, 55], enhancement [31, 56] etc.”
DEA-Net: Single Image Dehazing Based on Detail-Enhanced Convolution and Content-Guided Attention (2023, methodology): “In this section, we compare our DEA-Net with 4 earlier dehazing approaches including DCP [20], DehazeNet [2], AOD-Net [3], GFN [26] and 9 recent state-of-the-art (SOTA) single image dehazing methods including PFDN [24], FFA-Net [5], MSBDN [10], DMT-Net [41], AECR-Net [6], SGID-PFF [17], UDN [18],…”
Multi-Scale Boosted Dehazing Network With Dense Feature Fusion (2020, methodology): “Methods DCP [3] NLD [1] AODNet [6] MSCNN [13] MsPPN [19] DcGAN [8] GFN [14] GCANet [2] PFFNet [12] GDN [10] DuRN [11] Ours”
Domain Adaptation for Image Dehazing (2020, methodology): “From Figure 5 (b), we can observe that both NLD [2] and GFN [27] suffer from some color distortion where the result looks unrealistic.”
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing (2019, methodology): “The grid network has clear advantages over the encoderdecoder network and the conventional multi-scale network extensively used in image restoration [18, 41, 38, 27].”
CLEARER: Multi-Scale Neural Architecture Search for Image Restoration (2020, background): “As a matter of fact, the advances of image restoration in recent years are benefited from the developments of various handcrafted neural network architectures [27, 14, 15, 19, 24, 40, 31, 34].”
PSCC-Net: Progressive Spatio-Channel Correlation Network for Image Manipulation Detection and Localization (2021, background): “It has been widely adopted in many low-level and high-level vision tasks, such as denoising [5], [49], inpainting [50], super-resolution [51], [52], and object detection [53]–[56].”
Gated Context Aggregation Network for Image Dehazing and Deraining (2018, methodology): “[22] reformulates the atmospheric scattering model to predict the ﬁnal clean image through a light-weight CNN. [32] creates three different derived input images from the original hazy image and fuses the dehazed results out of these derived inputs.”
Vision Transformers for Single Image Dehazing (2022, methodology): “DehazeFormer-M [12, 12, 12, 6, 6] [24, 48, 96, 48, 24] [2, 4, 4, 2, 2] [1/4, 1/2, 3/4, 0, 0] [2, 4, 6, 1, 1] ConvBlock”
Deblurring by Realistic Blurring (2020, background): “Recently, deep learning methods have achieved a great success in the areas of object recognition [9, 44, 43, 19, 18] and image reconstruction including video deblurring [45], video dehazing [25], and other GAN-based generation tasks [29, 24, 39, 37].”
Contrastive Learning for Compact Single Image Dehazing (2021, methodology): “Most of them [37, 30, 34, 10] focus on strengthening the dehazing network and adopt clear images as positive samples to guide the dehazing network via image reconstruction loss without any regularization on images or features.”
FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing (2020, methodology): “The methods of GFN (Ren et al. 2018) and EPDN (Qu et al.”
Densely Connected Pyramid Dehazing Network (2018, methodology): “To overcome the degradations caused by haze, image and video-based haze removal algorithms have been proposed in the literature [33, 5, 42, 3, 13, 21, 27, 51, 24, 57, 8, 10, 9, 34].”
All-In-One Image Restoration for Unknown Corruption (2022, background): “Other image restoration tasks have also faced the similar challenge, such as debluring [2,12,29,32–34,36], deraining [10,17,24,42,46,49, 50,52], and dehazing [1,15,20,25,28,35,37,38].”
Enhanced Pix2pix Dehazing Network (2019, methodology): “GFN [16] rank the second in PSNR and the first in PI.”