LAP-Net: Level-Aware Progressive Network for Image Dehazing

Li, Yunan; Miao, Qiguang; Ouyang, Wanli; Ma, Zhenxin; Fang, Huijuan; Dong, Chao; Quan, Yining

doi:10.1109/iccv.2019.00337

Cited by 75 publications

(25 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [27] propose a grid network GridDehazeNet for single image dehazing, which consists of three modules, pre-processing, backbone, and post-processing. Li et al [61] introduce a level-aware progressive network (LAP-Net), of which each stage learns different levels of haze with different supervision and the final output is yielded with an adaptive integration strategy. Dong et al [62] propose a Multi-Scale Boosted Dehazing Network (MSBDN) based on the U-Net architecture with two principles, boosting and error feedback to realize dense feature fusion.…”

Section: Deep Learning Based Methodsmentioning

confidence: 99%

T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

Zheng¹,

Li²,

Luo³

2021

Preprint

View full text Add to dashboard Cite

Hazy images reduce the visibility of the image content, and haze will lead to failure in handling subsequent computer vision tasks. In this paper, we address the problem of image dehazing by proposing a dehazing network named T-Net, which consists of a backbone network based on the U-Net architecture and a dual attention module. And it can achieve multi-scale feature fusion by using skip connections with a new fusion strategy. Furthermore, by repeatedly unfolding the plain T-Net, Stack T-Net is proposed to take advantage of the dependence of deep features across stages via a recursive strategy. In order to reduce network parameters, the intra-stage recursive computation of ResNet is adopted in our Stack T-Net. And we take both the stage-wise result and the original hazy image as input to each T-Net and finally output the prediction of clean image. Experimental results on both synthetic and real-world images demonstrate that our plain T-Net and the advanced Stack T-Net perform favorably against the state-of-the-art dehazing algorithms, and show that our Stack T-Net could further improve the dehazing effect, demonstrating the effectiveness of the recursive strategy.

show abstract

Section: Deep Learning Based Methodsmentioning

confidence: 99%

T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

Zheng¹,

Li²,

Luo³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Image dehazing by supervised learning: Supervised learningbased image dehazing methods [10,12,20,22,27,28,37,38,40,42] need large-scale paired training samples. Daytime dehazing methods synthesize hazy samples from clear ones according to the imaging model, where the transmission is either assumed to be a constant within each local patch [10,33] or calculated from the scene depth [20,21,27,29].…”

Section: Related Workmentioning

confidence: 99%

“…Less progress has been made in nighttime dehazing than daytime dehazing, especially in the context of deep learning. For example, many convolutional neural networks (CNN)-based methods have been proposed for daytime dehazing [10,12,20,22,24,27,27,28,35,37,38,40,42]. The benefit of the strong representation capacity of CNN relies on large-scale training data.…”

Section: Introductionmentioning

confidence: 99%

Nighttime Dehazing with a Synthetic Benchmark

Zhang

Cao

Zha

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Convolutional Neural Networks (CNNs) is one of the typical algorithms of deep learning. Many methods (Cai et al, 2016;Deng et al, 2019;Dudhane & Murala, 2019;Liu et al, 2019;Ma et al, 2019;Park et al, 2020;Ren et al, 2016;Li, Miao, et al, 2019;Zhang & Patel, 2018) based on CNNs are proposed by people to estimate the parameters of the ASM. For example, DehazeNet proposed by Cai (Cai et al, 2016) et al is the first time using CNN to directly estimate the medium transmission map from the haze image to achieve the purpose of image dehazing.…”

Section: Related Workmentioning

confidence: 99%

Single image dehazing algorithm based on pyramid mutil-scale transposed convolutional network

Wang

Duan

Yang

2020

Systems Science & Control Engineering

View full text Add to dashboard Cite

In this paper, a novel single image dehazing method based on pyramid multi-scale transposed convolutional network (MST-Net) is proposed. Conventional haze removal algorithms based on the atmospheric scattering model may lead to some problems such as incomplete dehazing and colour distortion due to the inaccurate parameter approximations or indirect image optimization and reconstruction. Therefore, we design a real end-to-end image dehazing network to directly learn the mapping relationship between hazy images and the corresponding clear images. In this network, the cascaded feature extraction blocks extract the diversified feature information of the input images by multi-channel concatenation structure, which can effectively fuse the local features of the first convolution layer into the semantic features of subsequent layers in the block. In order to reconstruct high-quality dehazed images relieving the colour distortion, we design a multi-scale transposed convolution block to gradually expand the resolution of the obtained feature maps, and introduce skip connections from the feature extraction module to supplement the detailed information of the feature map pyramid. Extensive experimental results demonstrate that the proposed method in this paper can remove the haze completely and achieve superior performance in subjective and objective evaluation over the other state-of-the-art methods.

show abstract

LAP-Net: Level-Aware Progressive Network for Image Dehazing

Cited by 75 publications

References 40 publications

T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

T-Net: Deep Stacked Scale-Iteration Network for Image Dehazing

Nighttime Dehazing with a Synthetic Benchmark

Single image dehazing algorithm based on pyramid mutil-scale transposed convolutional network

Contact Info

Product

Resources

About