A Coarse-to-Fine Two-Stage Attentive Network for Haze Removal of Remote Sensing Images

Li, Yufeng; Chen, Xiang

doi:10.1109/lgrs.2020.3006533

Cited by 69 publications

(36 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we compare our method with seven classical dehazing methods, including some deep learning methods, and evalute them overall. The comparative typical methods including DCP [6,26], NLD [8,32], CAP [9], PFF-Net [12], W-U-Net [13], EPDN [14], and FCTF-Net [15]. Here, the guided image filtering [26] is applied to DCP to further improve the estimation accuracy of transmission.…”

Section: Results Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze

et al. 2021

View full text Add to dashboard Cite

The haze in remote sensing images can cause the decline of image quality and bring many obstacles to the applications of remote sensing images. Considering the non-uniform distribution of haze in remote sensing images, we propose a single remote sensing image dehazing method based on the encoder–decoder architecture, which combines both wavelet transform and deep learning technology. To address the clarity issue of remote sensing images with non-uniform haze, we preliminary process the input image by the dehazing method based on the atmospheric scattering model, and extract the first-order low-frequency sub-band information of its 2D stationary wavelet transform as an additional channel. Meanwhile, we establish a large-scale hazy remote sensing image dataset to train and test the proposed method. Extensive experiments show that the proposed method obtains greater advantages over typical traditional methods and deep learning methods qualitatively. For the quantitative aspects, we take the average of four typical deep learning methods with superior performance as a comparison object using 500 random test images, and the peak-signal-to-noise ratio (PSNR) value using the proposed method is improved by 3.5029 dB, and the structural similarity (SSIM) value is improved by 0.0295, respectively. Based on the above, the effectiveness of the proposed method for the problem of remote sensing non-uniform dehazing is verified comprehensively.

show abstract

Section: Results Evaluationmentioning

confidence: 99%

“…The original purpose of the above-mentioned methods is to dehaze the ground images. For the hazy RS images, Li et al [15] proposed a firstcoarse-then-fine two-stage dehazing network named FCTF-Net. In the first stage, the encoder-decoder architecture is used to extract multi-scale features.…”

Section: Dehazing Methods Based On Deep Learningmentioning

confidence: 99%

Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze

et al. 2021

View full text Add to dashboard Cite

show abstract

“…To objectively evaluate the aerial image dehazing performance, we compare our method with DCP [6], DehazeNet [19], FCTF [30] and CGAN [29]. Table 5 and Figure 7 show quantitative and qualitative results on the SateHaze1k dataset, respectively.…”

Section: ) Evaluation On Satehaze1k Datasetmentioning

confidence: 99%

“…datasets have been established, such as SateHaze1k (three levels of fog, namely thin, moderate, and thick fog) [29], UN-HAZE (uniform haze-clear image pairs) [30], and NONUN-HAZE (nonuniform haze-clear image pairs) [30]. On the other hand, the recent aerial image dehazing algorithms exhibit remarkable performance, such as MRCNN [32], H2RL-Net [31], and RSDehazeNet [16].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Haze Removal for Aerial Imagery Based on Asymmetric Contrastive CycleGAN

Xie

2022

IEEE Access

View full text Add to dashboard Cite

Aerial image dehazing is an important preprocessing step, since haze extremely degrades the imaging quality and affects subsequent the applications of aerial imagery. Most current haze removal methods achieve encouraging performance by relying on paired synthetic data, while are limited to their generality and scalability in the practical tasks. To this end, this paper aims to learn an effective unsupervised dehazing model from an unpaired set of clear and hazy aerial images. Motivated by the great advantages of contrastive learning in unsupervised representation field, we first attempt to formulate a Asymmetric Contrastive CycleGAN dehazing framework (namely ACC-GAN) to maximize the mutual information between the hazy domain and the haze-free domain. In the latent representation space, the introduced contrastive constraint ensures that the restored image is pulled closer to the clear image and pushed away from the hazy image, so as to indirectly regularize the unsupervised dehazing process. Importantly, different from the standard CycleGAN, we develop an additional feature transfer network into the forward path to form the asymmetric structure of ACC-GAN, which can enhance encoded features from hazy domain to haze-free domain. During training, multi-dimension loss terms are jointly built into a loss committee for generating dehazed results with higher naturalness and better fidelity. Experimental results on synthesis and real-world datasets indicate that our method is superior to existing unsupervised dehazing approaches, and is also very competitive to other related supervised models.INDEX TERMS aerial imagery; haze removal; asymmetric CycleGAN; unsupervised learning; contrastive learning.

show abstract

“…We employ 64 challenging images to address these challenges, and we compare ST-UNet with other state-of-the art dehazing DNNs, i.e., DehazeNet, (5) DEFADE, (12) SID, (13) NLD, (14) CAP, (15) PFF-Net, (16) W-U-Net, (17) and FCTF-Net. (18) We set the input image size to 512 × 512 for all DNNs as shown in Fig. 3.…”

Section: Quantitative Evaluationmentioning

confidence: 99%

Swin Transformer UNet for Very High Resolution Image Dehazing

Bian¹,

Zhang²,

Wang³

et al. 2022

Sensors and Materials

View full text Add to dashboard Cite

Rapid image acquisition for a region affected by an earthquake is important to manage the rescue operation. The use of an unmanned aerial vehicle (UAV) to rapidly cruise an affected region and obtain very high resolution (VHR) images is highly advantageous. However, haze is a problem for many UAV aerial images, especially when UAVs cross clouds. In this paper, we present a parallel predicting workflow that cooperates with Swin Transformer UNet (ST-UNet) for this task. ST-UNet utilizes the Swin Transformer instead of a convolutional layer (CNN), which greatly enhances the processing speed without accuracy loss. The predicting workflow employs parallel processing and a reasonable data structure to maximize the computing resources for rapid processing. To demonstrate the advantageousness of the proposed workflow, we employed three public remote sensing datasets for evaluation, and the proposed ST-UNet obtained the highest accuracy and speed. Furthermore, the high dehazing performance of ST-UNet was demonstrated using a real post-earthquake scene.

show abstract

A Coarse-to-Fine Two-Stage Attentive Network for Haze Removal of Remote Sensing Images

Cited by 69 publications

References 14 publications

Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze

Deep Dehazing Network for Remote Sensing Image with Non-Uniform Haze

Unsupervised Haze Removal for Aerial Imagery Based on Asymmetric Contrastive CycleGAN

Swin Transformer UNet for Very High Resolution Image Dehazing

Contact Info

Product

Resources

About