Search Results (58)

Single image dehazing is a fundamental task in computer vision, aiming to recover a clear scene from a hazy input image. To address the limitations of traditional dehazing algorithms—particularly in global feature association and local detail preservation—this study proposes a novel Transformer-based dehazing model enhanced by an interactive channel attention mechanism. The proposed architecture adopts a U-shaped encoder–decoder framework, incorporating key components such as a feature extraction module and a feature fusion module based on interactive attention. Specifically, the interactive channel attention mechanism facilitates cross-layer feature interaction, enabling the dynamic fusion of global contextual information and local texture details. The network architecture leverages a multi-scale feature pyramid to extract image information across different dimensions, while an improved cross-channel attention weighting mechanism enhances feature representation in regions with varying haze densities. Extensive experiments conducted on both synthetic and real-world datasets—including the RESIDE benchmark—demonstrate the superior performance of the proposed method. Quantitatively, it achieves PSNR gains of 0.53 dB for indoor scenes and 1.64 dB for outdoor scenes, alongside SSIM improvements of 1.4% and 1.7%, respectively, compared with the second-best performing method. Qualitative assessments further confirm that the proposed model excels in restoring fine structural details in dense haze regions while maintaining high color fidelity. These results validate the effectiveness of the proposed approach in enhancing both perceptual quality and quantitative accuracy in image dehazing tasks. Full article

Haze significantly degrades image quality by reducing contrast and blurring object boundaries, which impairs the performance of computer vision systems. Among various approaches, single-image dehazing remains particularly challenging due to the absence of depth information. While Vision Transformer (ViT)-based models have achieved remarkable results by leveraging multi-head attention and large effective receptive fields, their high computational complexity limits their applicability in real-time and embedded systems. To address this limitation, we propose MLKD-Net, a lightweight CNN-based model that incorporates a novel Multi-Head Large Kernel Block (MLKD), which is based on the Multi-Head Large Kernel Attention (MLKA) mechanism. This structure preserves the benefits of large receptive fields and a multi-head design while also ensuring compactness and computational efficiency. MLKD-Net achieves a PSNR of 37.42 dB on the SOTS-Outdoor dataset while using 90.9% fewer parameters than leading Transformer-based models. Furthermore, it demonstrates real-time performance with 55.24 ms per image (18.2 FPS) on the NVIDIA Jetson Orin Nano in TensorRT-INT8 mode. These results highlight its effectiveness and practicality for resource-constrained, real-time image dehazing applications. Full article

In remote sensing single-image dehazing (RSSID), adjacency effects and the multi-scale characteristics of the land surface–atmosphere system highlight the importance of a network’s effective receptive field (ERF) and its ability to capture multi-scale features. Although multi-scale hybrid models combining convolutional neural networks and Transformers show promise, the quadratic complexity of Transformer complicates the balance between ERF and efficiency. Recently, Mamba achieved global ERF with linear complexity and excelled in modeling long-range dependencies, yet its design for sequential data and channel redundancy limits its direct applicability to RSSID. To overcome these challenges and improve performance in RSSID, we present a novel Mamba-based dehazing network, U-shaped Dual Attention Vision Mamba Network (UDAVM-Net) for Satellite RSSID, which integrates multi-path scanning and incorporates dual attention mechanisms to better capture non-uniform haze features while reducing redundancy. The core module, Residual Vision Mamba Blocks (RVMBs), are stacked within a U-Net architecture to enhance multi-scale feature learning. Furthermore, to enhance the model’s applicability to real-world remote sensing data, we abandoned overly simplified haze image degradation models commonly used in existing works, instead adopting an atmospheric radiative transfer model combined with a cloud distortion model to construct a submeter-resolution satellite RSSID dataset. Experimental results demonstrate that UDAVM-Net consistently outperforms competing methods on the StateHaze1K dataset, our newly proposed dataset, and real-world remote sensing images, underscoring its effectiveness in diverse scenarios. Full article

Deploying high-performance image restoration models on drones is critical for applications like autonomous navigation, surveillance, and environmental monitoring. However, the computational and memory limitations of drones pose significant challenges to utilizing complex image restoration models in real-world scenarios. To address this issue, we propose the Simultaneous Learning Knowledge Distillation (SLKD) framework, specifically designed to compress image restoration models for resource-constrained drones. SLKD introduces a dual-teacher, single-student architecture that integrates two complementary learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL). In DRL, the student encoder learns to eliminate degradation factors by mimicking Teacher A, which processes degraded images utilizing a BRISQUE-based extractor to capture degradation-sensitive natural scene statistics. Concurrently, in IRL, the student decoder reconstructs clean images by learning from Teacher B, which processes clean images, guided by a PIQE-based extractor that emphasizes the preservation of edge and texture features essential for high-quality reconstruction. This dual-teacher approach enables the student model to learn from both degraded and clean images simultaneously, achieving robust image restoration while significantly reducing computational complexity. Experimental evaluations across five benchmark datasets and three restoration tasks—deraining, deblurring, and dehazing—demonstrate that, compared to the teacher models, the SLKD student models achieve an average reduction of 85.4% in FLOPs and 85.8% in model parameters, with only a slight average decrease of 2.6% in PSNR and 0.9% in SSIM. These results highlight the practicality of integrating SLKD-compressed models into autonomous systems, offering efficient and real-time image restoration for aerial platforms operating in challenging environments. Full article

Current advancements in image processing technologies have led to significant progress; however, adverse weather conditions, including haze, snow, and rain, often degrade image quality, which in turn impacts the performance of deep learning-based image matching algorithms. Most existing methods attempt to correct blurred images prior to target detection, which increases network complexity and may result in the loss of potentially crucial information. To better integrate image restoration and image matching tasks, this paper presents DeMatchNet, an end-to-end integrated network framework that seamlessly combines the feature fusion attention network for single image dehazing (FFA-Net) dehazing module with the detector-free local feature matching with transformers (LoFTR) feature matching module. The proposed framework first designs an attention-based feature fusion module (FFM), which effectively merges the original hazy features with the dehazed features. This ensures that the generated dehazed features not only have improved visual quality, but also provide higher-quality input for subsequent feature matching. Subsequently, a feature alignment module (FA) performs scale and semantic adjustments on the fused features, enabling efficient sharing with the LoFTR module. This deep collaboration between dehazing and feature matching significantly reduces computational redundancy and enhances the overall performance. Experimental results on synthetic hazy datasets (based on MegaDepth and ETH3D) and real-world hazy datasets demonstrate that DeMatchNet outperforms the existing methods in terms of matching accuracy and robustness, showcasing its superior performance under challenging weather conditions. Full article

Single-image dehazing is an ill-posed problem that has attracted a myriad of research efforts. However, virtually all methods proposed thus far assume that input images are already affected by haze. Little effort has been spent on autonomous single-image dehazing. Even though deep learning dehazing models, with their widely claimed attribute of generalizability, do not exhibit satisfactory performance on images with various haze conditions. In this paper, we present a novel approach for autonomous single-image dehazing. Our approach consists of four major steps: sharpness enhancement, adaptive dehazing, image blending, and adaptive tone remapping. A global haze density weight drives the adaptive dehazing and tone remapping to handle images with various haze conditions, including those that are haze-free or affected by mild, moderate, and dense haze. Meanwhile, the proposed approach adopts patch-based haze density weights to guide the image blending, resulting in enhanced local texture. Comparative performance analysis with state-of-the-art methods demonstrates the efficacy of our proposed approach. Full article

Haze weather deteriorates image quality, causing images to become blurry with reduced contrast. This makes object edges and features unclear, leading to lower detection accuracy and reliability. To enhance haze removal effectiveness, we propose an image dehazing and fusion network based on the encoder–decoder paradigm (UIDF-Net). This network leverages the Image Fusion Module (MDL-IFM) to fuse the features of dehazed images, producing clearer results. Additionally, to better extract haze information, we introduce a haze encoder (Mist-Encode) that effectively processes different frequency features of images, improving the model’s performance in image dehazing tasks. Experimental results demonstrate that the proposed model achieves superior dehazing performance compared to existing algorithms on outdoor datasets. Full article

Single-image dehazing is a pivotal challenge in computer vision that seeks to remove haze from images and restore clean background details. Recognizing the limitations of traditional physical model-based methods and the inefficiencies of current attention-based solutions, we propose a new dehazing network combining an innovative Haze-Aware Attention Module (HAAM) with a Multiscale Frequency Enhancement Module (MFEM). The HAAM is inspired by the atmospheric scattering model, thus skillfully integrating physical principles into high-dimensional features for targeted dehazing. It picks up on latent features during the image restoration process, which gives a significant boost to the metrics, while the MFEM efficiently enhances high-frequency details, thus sidestepping wavelet or Fourier transform complexities. It employs multiscale fields to extract and emphasize key frequency components with minimal parameter overhead. Integrated into a simple U-Net framework, our Haze-Aware Attention Network (HAA-Net) for single-image dehazing significantly outperforms existing attention-based and transformer models in efficiency and effectiveness. Tested across various public datasets, the HAA-Net sets new performance benchmarks. Our work not only advances the field of image dehazing but also offers insights into the design of attention mechanisms for broader applications in computer vision. Full article

Despite their proficiency with typical environmental datasets, deep learning-based object detection algorithms struggle when faced with diverse adverse weather conditions. Moreover, existing methods often address single adverse weather scenarios, neglecting situations involving multiple concurrent adverse conditions. To tackle these challenges, we propose an enhanced approach to object detection in power construction sites under various adverse weather conditions, dubbed IDP-YOLOV9. This model leverages a parallel architecture comprising the Image Dehazing and Enhancement Processing (IDP) module and an improved YOLOV9 object detection module. Specifically, for images captured in adverse weather, our approach employs a parallel architecture that includes the Three-Weather Removal Algorithm (TRA) module and the Deep Learning-based Image Enhancement (DLIE) module, which, together, filter multiple weather factors to enhance image quality. Subsequently, we introduce an improved YOLOV9 detection network module that incorporates a three-layer routing attention mechanism for object detection. Experiments demonstrate that the IDP module significantly improves image quality by mitigating the impact of various adverse weather conditions. Compared to traditional single-processing models, our method improves recognition accuracy on complex weather datasets by 6.8% in terms of mean average precision (mAP50). Full article

In adverse foggy weather conditions, images captured are adversely affected by natural environmental factors, resulting in reduced image contrast and diminished visibility. Traditional image dehazing methods typically rely on prior knowledge, but their efficacy diminishes in practical, complex environments. Deep learning methods have shown promise in single-image dehazing tasks, but often struggle to fully leverage depth and edge information, leading to blurred edges and incomplete dehazing effects. To address these challenges, this paper proposes a deep-guided bilateral grid feature fusion dehazing network. This network extracts depth information through a dedicated module, derives bilateral grid features via Unet, employs depth information to guide the sampling of bilateral grid features, reconstructs features using a dedicated module, and finally estimates dehazed images through two layers of convolutional layers and residual connections with the original images. The experimental results demonstrate the effectiveness of the proposed method on public datasets, successfully removing fog while preserving image details. Full article

When light propagates in a scattering medium such as haze, it is partially scattered and absorbed, resulting in a decrease in the intensity of the light emitted by the imaging target and an increase in the intensity of the scattered light. This phenomenon leads to a significant reduction in the quality of images taken in hazy environments. To describe the physical process of image degradation in haze, the atmospheric scattering model is proposed. However, the accuracy of the model applied to the usual fog image restoration is affected by many factors. In general, fog images, atmospheric light, and haze transmittances vary spatially, which makes it difficult to calculate the influence of the accuracy of parameters in the model on the recovery accuracy. In this paper, the atmospheric scattering model was applied to the restoration of hazed images with a single transmittance. We acquired hazed images with a single transmittance from 0.05 to 1 using indoor experiments. The dehazing stability of the atmospheric scattering model was investigated by adjusting the atmospheric light and transmittance parameters. For each transmittance, the relative recovery accuracy of atmospheric light and transmittance were calculated when they deviated from the optimal value of 0.1, respectively. The maximum parameter estimation deviations allowed us to obtain the best recovery accuracies of 90%, 80%, and 70%. Full article

Numerous extant image dehazing methods based on learning improve performance by increasing the depth or width, the size of the convolution kernel, or using the Transformer structure. However, this will inevitably introduce many parameters and increase the computational overhead. Therefore, we propose a lightweight dehazing framework: Dehaze-UNet, which has excellent dehazing performance and very low computational overhead to be suitable for terminal deployment. To allow Dehaze-UNet to aggregate the features of haze, we design a LAYER module. This module mainly aggregates the haze features of different hazy images through the batch normalization layer, so that Dehaze-UNet can pay more attention to haze. Furthermore, we revisit the use of the physical model in the network. We design an ASMFUN module to operate the feature map of the network, allowing the network to better understand the generation and removal of haze and learn prior knowledge to improve the network’s generalization to real hazy scenes. Extensive experimental results indicate that the lightweight Dehaze-UNet outperforms state-of-the-art methods, especially for hazy images of real scenes. Full article

Image dehazing is an effective means to enhance the quality of images captured in foggy or hazy weather conditions. However, the existing dehazing methods either cannot obtain satisfactory recovery results or have large model parameters. This limits the application of the model on resource-limited platforms. To overcome these limitations, we propose a lightweight yet effective image-dehazing method, named the lightweight detail–content progressive coupled network (LDPC-Net). Within the framework of LDPC-Net, we propose a progressive coupling dehazing paradigm. Specifically, we first estimate the details and content information of the haze-free image, and then fuse these estimations using the progressive coupling method. This proposed dehazing framework markedly enhances the operational efficiency of the model. Meanwhile, considering both the effectiveness and efficiency of the network, we also design a lightweight adaptive feature extraction block serving as the basic feature extraction module of the proposed LDPC-Net. Extensive experimental results demonstrate the effectiveness of our LDPC-Net, outperforming the state-of-the-art methods by boosting the PSNR index over 38.57 dB with only 0.708 M parameters. Full article

This paper aimed to develop a method for generating sand–dust removal and dehazed images utilizing CycleGAN, facilitating object identification on roads under adverse weather conditions such as heavy dust or haze, which severely impair visibility. Initially, the study addressed the scarcity of paired image sets for training by employing unpaired CycleGAN training. The CycleGAN training module incorporates hierarchical single-scale Retinex (SSR) images with varying sigma sizes, facilitating multiple-scaled trainings. Refining the training data into detailed hierarchical layers for virtual paired training enhances the performance of CycleGAN training. Conventional sand–dust removal or dehazing algorithms, alongside deep learning methods, encounter challenges in simultaneously addressing sand–dust removal and dehazing with a singular algorithm. Such algorithms often necessitate resetting hyperparameters to process images from both scenarios. To overcome this limitation, we proposed a unified approach for removing sand–dust and haze phenomena using a single model, leveraging images processed hierarchically with SSR. The image quality and image sharpness metrics of the proposed method were BRIQUE, PIQE, CEIQ, MCMA, LPC-SI, and S3. In sand–dust environments, the proposed method achieved the highest scores, with an average of 21.52 in BRISQUE, 0.724 in MCMA, and 0.968 in LPC-SI compared to conventional methods. For haze images, the proposed method outperformed conventional methods with an average of 3.458 in CEIQ, 0.967 in LPC-SI, and 0.243 in S3. The images generated via this proposed method demonstrated superior performance in image quality and sharpness evaluation compared to conventional algorithms. The outcomes of this study hold particular relevance for camera images utilized in automobiles, especially in the context of self-driving cars or CCTV surveillance systems. Full article

Numerous single-image dehazing algorithms have been developed, employing a spectrum of techniques ranging from intricate physical computations to state-of-the-art deep-learning methodologies. However, conventional deep-learning approaches, particularly those based on standard convolutional neural networks (CNNs), often result in the persistence of residual fog patches when applied to images featuring high fog concentration or heterogeneous fog distribution. In response to this challenge, we propose an innovative solution known as the multi-feature fusion image dehazing network (MFID-Net). This approach employs an end-to-end methodology to directly capture the mapping relationship between hazy and fog-free images. Central to our approach is the introduction of a novel multi-feature fusion (MF) module, strategically designed to address channel and pixel characteristics in regions with uneven or high fog concentrations. Notably, this module achieves effective haze reduction while minimizing computational resources, thereby mitigating the issue of residual fog patches. Experimental results underscore the superior performance of our algorithm compared to similar dehazing methods, as evidenced by higher scores in structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and computational velocity. Moreover, MFID-Net exhibits significant advancements in restoring details within expansive monochromatic areas, such as skies and white walls. Full article