Haze Distribution Research Articles

A Haze Intensity Sensing and Texture Enhanced Transformer for Image Dehazing

The degradation of images captured in hazy weather can severely affect practical applications. However, most existing learning-based methods ignore the varied haze distribution in an image, resulting in incomplete dehazing of some areas. Also, the presence of haze can blur the textures and details, which will heavily impact the subsequent image processing. In this paper, we propose a transformer-based framework for dehazing tasks called HITFormer. Firstly, we introduce a texture recovery and enhance module as a preprocess to strengthen details. Then, we propose an adaptive haze intensity prediction subnet to predict the haze intensity of different areas. Lastly, we use a semantic-based luminance and chrominance adjustment module to fuse the feature maps in YUV color space and form a transformation coefficient to get a recovery image. The extensive experiments demonstrate that our HITFormer achieves state-of-the-art performance on several image dehazing datasets.

IHR-Net: Image haze removal network based on improved YUV spatial strategy

Abstract Image haze removal is a challenging task in computer vision. Existing dehazing algorithms are typically applied in the RGB space, assuming that haze affects all color channels equally, and thus enhancing the image independently across the three channels. Actually, compared to the RGB space, the YUV domain can provide a more accurate representation of haze distribution characteristics and is better suited for image haze removal. Nevertheless, current YUV-based dehazing strategies often suffer from dull colors due to a lack of comprehensive consideration of color channels. To address this limitation, we propose an improved YUV domain-based image haze removal network (IHR-Net), which consists of a pre-trained model and a backbone network to enhance the Y channel and UV channels separately. Specifically, we utilize the pre-trained model to extract haze features that guide the backbone network in optimizing the UV channels. To increase the network's attention to color-shifting areas, we introduce a haze attention module (HAM) and integrate it into the backbone network. Experimental results on both synthetic and real-world daytime and nighttime images demonstrate the superior performance of IHR-Net.

MABDT: Multi-scale attention boosted deformable transformer for remote sensing image dehazing

MABDT: Multi-scale attention boosted deformable transformer for remote sensing image dehazing

Global feature fusion generative adversarial network for underwater image enhancement

AbstractMost CNN‐based networks treat features in different channels and pixels similarly. However, the dispersion of light underwater results in uneven haze distribution throughout the images. To alleviate these problems, the global feature fusion generative adversarial network is proposed, to separate and enhance the global feature by channels and pixels simultaneously. The key novelty of our method is utilizing the attention mechanism to emphasize features in different channels and pixels in fusion block, which allocates higher weights to more important features. The network's reliability is further optimized through the incorporation of condition information to restrict the training of the network. Both qualitative and quantitative evaluations verify that the proposed method is capable of greater visual quality compared with other classic and state‐of‐the‐art methods.

Dehazing Ultrasound Using Diffusion Models.

Echocardiography has been a prominent tool for the diagnosis of cardiac disease. However, these diagnoses can be heavily impeded by poor image quality. Acoustic clutter emerges due to multipath reflections imposed by layers of skin, subcutaneous fat, and intercostal muscle between the transducer and heart. As a result, haze and other noise artifacts pose a real challenge to cardiac ultrasound imaging. In many cases, especially with difficult-to-image patients such as patients with obesity, a diagnosis from B-Mode ultrasound imaging is effectively rendered unusable, forcing sonographers to resort to contrast-enhanced ultrasound examinations or refer patients to other imaging modalities. Tissue harmonic imaging has been a popular approach to combat haze, but in severe cases is still heavily impacted by haze. Alternatively, denoising algorithms are typically unable to remove highly structured and correlated noise, such as haze. It remains a challenge to accurately describe the statistical properties of structured haze, and develop an inference method to subsequently remove it. Diffusion models have emerged as powerful generative models and have shown their effectiveness in a variety of inverse problems. In this work, we present a joint posterior sampling framework that combines two separate diffusion models to model the distribution of both clean ultrasound and haze in an unsupervised manner. Furthermore, we demonstrate techniques for effectively training diffusion models on radio-frequency ultrasound data and highlight the advantages over image data. Experiments on both in-vitro and in-vivo cardiac datasets show that the proposed dehazing method effectively removes haze while preserving signals from weakly reflected tissue.

Feature Fusion Image Dehazing Network Based on Hybrid Parallel Attention

Most of the existing dehazing methods ignore some global and local detail information when processing images and fail to fully combine feature information at different levels, which leads to contrast imbalance and residual haze in the dehazed images. To this end, this article proposes a image dehazing network based on hybrid parallel attention feature fusion, called the HPA-HFF network. This network is an optimization of the basic network, FFA-Net. First, the hybrid parallel attention (HPA) module is introduced, which uses parallel connections to mix different types of attention mechanisms, which can not only enhance the extraction and fusion capabilities of global spatial context information but also enhance the expression capabilities of features and have better dehazing effects on uneven distribution of haze. Second, the hierarchical feature fusion (HFF) module is introduced, which dynamically fuses feature maps from different paths to adaptively increase their receptive field and refine and enhance image features. Experimental results demonstrate that the HPA-HFF network proposed in this article is contrasted with eight mainstream dehazing networks on the public dataset RESIDE. The HPA-HFF network achieves the highest PSNR (39.41) and SSIM (0.9967) and obtains a good dehazing effect in subjective vision.

Multi-scale large kernel convolution and hybrid attention network for remote sensing image dehazing

Multi-scale large kernel convolution and hybrid attention network for remote sensing image dehazing

Multi‐scale feature aggregation network for single‐image dehazing

AbstractTransformer possesses a broader perceptual scope, while the Convolutional Neural Network (CNN) excels at capturing local information. In this paper, the authors propose the Multi‐Sclale Feature Aggregation Network (MSFA‐Net) for single‐image dehazing which is fused with the advantages of Transformer and CNN. Our MSFA‐Net is based on the encoder–decoder structure, and there are four main innovations. Firstly, the authors make some improvements to the original Swin Transformer to make it more effective for dehazing tasks, and the authors name it Spatial Information Aggregation Transformer (SIAT). The authors place the SIAT in both encoder and decoder of MSFA‐Net for feature extraction. The authors propose an upsampling module called Efficient Spatial Resolution Recovery (ESRR) which is placed in the decoder part. Compared to commonly used transposed convolutions, the authors’ ESRR module has fewer computational cost. Considering that the haze distribution is always uneven and the information from each channel is different, the authors introduce the Dynamic Multi‐Attention (DMA) module to provide pixel‐wise weights and channel‐wise weights for input features. The authors place the DMA module between the encoder and decoder parts. As the network depth increases, the spatial structural information from the high‐resolution layer tends to degrade. To deal with the problem, the authors propose the Multi‐Scale Feature Fusion (MSFF) module to recover missing spatial structural information. The authors place the MSFF module in both the encoder and decoder parts. Extensive experimental results show that the authors’ proposed dehazing network achieves state‐of‐the‐art dehazing performance with relatively low computational cost.

Atmospheric scattering model and dark channel prior constraint network for environmental monitoring under hazy conditions

Environmental monitoring systems based on remote sensing technology have a wider monitoring range and longer timeliness, which makes them widely used in the detection and management of pollution sources. However, haze weather conditions degrade image quality and reduce the precision of environmental monitoring systems. To address this problem, this research proposes a remote sensing image dehazing method based on the atmospheric scattering model and a dark channel prior constrained network. The method consists of a dehazing network, a dark channel information injection network (DCIIN), and a transmission map network. Within the dehazing network, the branch fusion module optimizes feature weights to enhance the dehazing effect. By leveraging dark channel information, the DCIIN enables high-quality estimation of the atmospheric veil. To ensure the output of the deep learning model aligns with physical laws, we reconstruct the haze image using the prediction results from the three networks. Subsequently, we apply the traditional loss function and dark channel loss function between the reconstructed haze image and the original haze image. This approach enhances interpretability and reliability while maintaining adherence to physical principles. Furthermore, the network is trained on a synthesized non-homogeneous haze remote sensing dataset using dark channel information from cloud maps. The experimental results show that the proposed network can achieve better image dehazing on both synthetic and real remote sensing images with non-homogeneous haze distribution. This research provides a new idea for solving the problem of decreased accuracy of environmental monitoring systems under haze weather conditions and has strong practicability.

WaveletFormerNet: A Transformer-based wavelet network for real-world non-homogeneous and dense fog removal

WaveletFormerNet: A Transformer-based wavelet network for real-world non-homogeneous and dense fog removal

A modified atmospheric scattering model and degradation image clarification algorithm for haze environments

A modified atmospheric scattering model and degradation image clarification algorithm for haze environments

One-dimensional Microphysics Model of Venusian Clouds from 40 to 100 km: Impact of the Middle-atmosphere Eddy Transport and SOIR Temperature Profile on the Cloud Structure

We conducted a simulation of H2SO4 vapor, H2O vapor, and H2SO4–H2O liquid aerosols from 40 to 100 km, using a 1D Venus cloud microphysics model based on the one detailed in Imamura & Hashimoto. The cloud distribution obtained is in good agreement with in situ observations by Pioneer Venus and remote-sensing observations from Venus Express (VEx). Case studies were conducted to investigate sensitivities to atmospheric parameters, including eddy diffusion and temperature profiles. We find that efficient eddy transport is important for determining upper haze population and its microphysical properties. Using the recently updated eddy diffusion coefficient profile by Mahieux et al., our model replicates the observed upper haze distribution. The H2O vapor distribution is highly sensitive to the eddy diffusion coefficient in the 60–70 km region. This indicates that updating the eddy diffusion coefficient is crucial for understanding the H2O vapor transport through the cloud layer. The H2SO4 vapor abundance varies by several orders of magnitude above 85 km, depending on the temperature profile. However, its maximum value aligns well with observational upper limits found by Sandor et al., pointing to potential sources other than H2SO4 aerosols in the upper haze layer that contribute to the SO2 inversion layer. The best-fit eddy diffusion profile is determined to be ∼2 m2 s−1 between 60 and 70 km and ∼360 m2 s−1 above 85 km. Furthermore, the observed increase of H2O vapor concentration above 85 km is reproduced by using the temperature profile from the VEx/SOIR instrument.

Haze Optical Depth in Exoplanet Atmospheres Varies with Rotation Rate: Implications for Observations

Transmission spectroscopy supports the presence of uncharacterized, light-scattering and -absorbing hazes in the atmospheres of many exoplanets. The complexity of factors influencing the formation, 3D transport, radiative impact, and removal of hazes makes it challenging to match theoretical models to the existing data. Our study simplifies these factors to focus on the interaction between planetary general circulation and haze distribution at the planetary limb. We use an intermediate-complexity general circulation model, ExoPlaSim, to simulate idealized organic haze particles as radiatively active tracers in the atmospheres of tidally locked terrestrial planets for 32 rotation rates. We find three distinct 3D spatial haze distributions, corresponding to three circulation regimes, each with a different haze profile at the limb. All regimes display significant terminator asymmetry. In our parameter space, super-Earth-sized planets with rotation periods greater than 13 days have the lowest haze optical depths at the terminator, supporting the choice of slower rotators as observing targets.

End-to-End Detail-Enhanced Dehazing Network for Remote Sensing Images

Space probes are always obstructed by floating objects in the atmosphere (clouds, haze, rain, etc.) during imaging, resulting in the loss of a significant amount of detailed information in remote sensing images and severely reducing the quality of the remote sensing images. To address the problem of detailed information loss in remote sensing images, we propose an end-to-end detail enhancement network to directly remove haze in remote sensing images, restore detailed information of the image, and improve the quality of the image. In order to enhance the detailed information of the image, we designed a multi-scale detail enhancement unit and a stepped attention detail enhancement unit, respectively. The former extracts multi-scale information from images, integrates global and local information, and constrains the haze to enhance the image details. The latter uses the attention mechanism to adaptively process the uneven haze distribution in remote sensing images from three dimensions: deep, middle and shallow. It focuses on effective information such as haze and high frequency to further enhance the detailed information of the image. In addition, we embed the designed parallel normalization module in the network to further improve the dehazing performance and robustness of the network. Experimental results on the SateHaze1k and HRSD datasets demonstrate that our method effectively handles remote sensing images obscured by various levels of haze, restores the detailed information of the images, and outperforms the current state-of-the-art haze removal methods.

Improved RefineDNet algorithm for precise environmental perception of autonomous earthmoving machinery under haze and fugitive dust conditions

Improved RefineDNet algorithm for precise environmental perception of autonomous earthmoving machinery under haze and fugitive dust conditions

Real-World Non-Homogeneous Haze Removal by Sliding Self-Attention Wavelet Network

In complex natural haze scenes, image haze removal still faces significant challenges in removing non-homogeneous and dense haze. The double complexity of haze distribution, on the one hand, is reflected in the interference of haze to the global image information, and on the other hand, it is reflected in the imbalance of image brightness and color caused by random haze distribution. In natural scenes with prominent edge and texture features, the above problems may cause severe degradation of image quality and performance of various tasks. Numerous studies on network learning show that the effect of haze removal is closely related to haze feature expression. Therefore, to improve the performance of dehazing, this paper proposes a sliding self-attention wavelet network. Specifically, we first design a sliding self-attention module to identify haze regions in images and capture rich haze-related feature information. Then, considering the uneven distribution of haze in images, discrete wavelet transform (DWT) and inverse transform (IDWT) are used for constructing a hierarchical encoder-decoder structure, which can fully use the multi-resolution characteristics of DWT, locally decompose feature maps of different scales, extract low and high-frequency information, and then gradually recover sharp edges and precise texture details from hazy images. Finally, to enable the proposed network to generate more realistic haze-free images on different complex haze scenes, we develop a DWT-based adversarial loss function to constrain the low and high-frequency components of generated images closer to the corresponding clear images. Experimental results on the relevant public benchmark datasets show that the proposed algorithm achieves favorable dehazing performance.

Haze removal using deep convolutional neural network for Korea Multi-Purpose Satellite-3A (KOMPSAT-3A) multispectral remote sensing imagery

This paper presents a convolutional neural network to automatically remove the haze distribution using a single multispectral remote sensing image in the raw file format. To train the proposed dehazing network, we synthesized multispectral hazy images using the haze thickness map (HTM) and relative scattering model representing the wavelength-dependent scattering property of the haze distribution. Since the raw multispectral hazy images have a low dynamic range, we cannot accurately estimate the haze distribution directly from them. To differently impose a proper amount of attention to hazy and haze-free regions, we used the HTM from the contrast-enhanced version of the input hazy image. The proposed dehazing network consists of four sub-networks: (i) shallow feature extraction network (SFEN), (ii) cascaded residual dense block network (CRDBN), (iii) multiscale feature extraction network (MFEN), and (iv) refinement network (RN). The densely connected convolutional layers and local residual learning allow the residual dense block (RDB) to extract the abundant local features, and the cascaded architecture further improves the propagation of the local information and gradients. The MFEN is used to extract multiscale local features representing the hierarchical information for the haze distribution and haze-free region. Experimental results demonstrated that the proposed method can achieve improved dehazing performance on Korea Multi-Purpose Satellite-3A (KOMPSAT-3A) multispectral remote sensing imagery without undesired artifacts. In the sense of quantitative assessment, the proposed method produced improved peak signal-to-noise ratio (PSNR) by 10%, structural similarity index measure (SSIM) by 1%, and spectral angle mapper (SAM) by 19% compared with the existing best method.

Physical model and image translation fused network for single-image dehazing

The visibility and contrast of images captured in adverse weather such as haze or fog degrade dramatically, which further hinders the accomplishment of high-level computer vision tasks such as object detection and semantic segmentation in these conditions. Many methods have been proposed to solve image dehazing problem by using image translation networks or physical model embedding in CNNs. However, the physical model cannot effectively describe the hazy generation process in complex scenes and estimating the model parameters with only a hazy image is an ill-posed problem. Image translation-based methods may lead to artefacts or colour shifts in the recovered results without the guidance or constraints of physical model information. In this paper, an end-to-end physical model and image translation fused network is proposed to generate realistic haze-free images. Since the transmission map can express the haze distribution in the scene, the proposed method adopts an encoder with a multiscale residual block to extract hazy image features, and two separate decoders to recover a clear image and to estimate the transmission map. The multiscale features of the transmission map and image translation are fused to guide the decode processes with a conditional attention feature fusion block, which is composed of sequential channelwise and spatialwise attention. Moreover, a multitask and multiscale deep supervision mechanism is adopted to enhance the feature fusion and recover more image details. The algorithm can efficiently fuse the physical model information and the hazy image translation to address the problem existent in the methods only based on physical model embedding or direct image translation. Experimental results on the visual quality enhancement of hazy images and semantic segmentation tasks in hazy scenes demonstrate that our model can efficiently recover haze-free images, while performing on par with state-of-the-art methods.

Semi-supervised atmospheric component learning in low-light image problem.

Ambient lighting conditions play a crucial role in determining the perceptual quality of images from photographic devices. In general, inadequate transmission light and undesired atmospheric conditions jointly degrade the image quality. If we know the desired ambient factors associated with the given low-light image, we can recover the enhanced image easily. Typical deep networks perform enhancement mappings without investigating the light distribution and color formulation properties. This leads to a lack of image instance-adaptive performance in practice. On the other hand, physical model-driven schemes suffer from the need for inherent decompositions and multiple objective minimizations. Moreover, the above approaches are rarely data efficient or free of postprediction tuning. Influenced by the above issues, this study presents a semisupervised training method using no-reference image quality metrics for low-light image restoration. We incorporate the classical haze distribution model to explore the physical properties of the given image to learn the effect of atmospheric components and minimize a single objective for restoration. We validate the performance of our network for six widely used low-light datasets. Experimental studies show that our proposed study achieves a competitive performance for no-reference metrics compared to current state-of-the-art methods. We also show the improved generalization performance of our proposed method which is efficient in preserving face identities in extreme low-light scenarios.

Dynamic Multi-Attention Dehazing Network with Adaptive Feature Fusion

This paper proposes a Dynamic Multi-Attention Dehazing Network (DMADN) for single image dehazing. The proposed network consists of two key components, the Dynamic Feature Attention (DFA) module, and the Adaptive Feature Fusion (AFF) module. The DFA module provides pixel-wise weights and channel-wise weights for input features, considering that the haze distribution is always uneven in a degenerated image and the value in each channel is different. We propose an AFF module based on the adaptive mixup operation to restore the missing spatial information from high-resolution layers. Most previous works have concentrated on increasing the scale of the model to improve dehazing performance, which makes it difficult to apply in edge devices. We introduce contrastive learning in our training processing, which leverages both positive and negative samples to optimize our network. The contrastive learning strategy could effectively improve the quality of output while not increasing the model’s complexity and inference time in the testing phase. Extensive experimental results on the synthetic and real-world hazy images demonstrate that DMADN achieves state-of-the-art dehazing performance with a competitive number of parameters.