Visibility Restoration Research Articles

Multi-Weather Visibility Restoration using MPRNet - Multi-Stage Progressive Image Restoration

This paper introduces a novel approach, termed Multi-Stage Progressive Image Restoration (MSPIR), aimed at addressing the challenging task of restoring images degraded by various adverse weather conditions. Leveraging a combination of advanced algorithms including HI-Net, DCP, and MSCIA, MSPIR offers a comprehensive solution for mitigating the effects of fog, haze, rain streaks, and other atmospheric distortions on image visibility. The methodology follows a multi-stage iterative process, progressively refining image quality and enhancing visibility through successive stages of processing. By integrating deep learning techniques and adaptive context aggregation mechanisms, MSPIR achieves superior results in restoring image clarity and preserving fine details across diverse weather conditions. Experimental evaluations demonstrate the efficacy and robustness of the proposed framework, highlighting its potential for real-world applications in autonomous navigation, surveillance, and remote sensing. Looking ahead, future research directions include optimizing MSPIR for real-time applications, exploring novel deep learning architectures, and integrating additional sensory modalities to further enhance visibility restoration capabilities. Overall, MSPIR represents a significant advancement in multi-weather visibility restoration, offering promising prospects for clearer and safer image processing in various domains.

Computational Polarization Imaging In Vivo through Surgical Smoke Using Refined Polarization Difference.

In surgery, the surgical smoke generated during tissue dissection and hemostasis can degrade the image quality, affecting tissue visibility and interfering with the further image processing. Developing reliable and interpretable computational imaging methods for restoring smoke-affected surgical images is crucial, as typical image restoration methods relying on color-texture information are insufficient. Here a computational polarization imaging method through surgical smoke is demonstrated, including a refined polarization difference estimation based on the discrete electric field direction, and a corresponding prior-based estimation method, for better parameter estimation and image restoration performance. Results and analyses for ex vivo, the first in vivo animal experiments, and human oral cavity tests show that the proposed method achieves visibility restoration and color recovery of higher quality, and exhibits good generalization across diverse imaging scenarios with interpretability. The method is expected to enhance the precision, safety, and efficiency of advanced image-guided and robotic surgery.

Image fusion-based low-dose CBCT enhancement method for visualizing miniscrew insertion in the infrazygomatic crest

Digital dental technology covers oral cone-beam computed tomography (CBCT) image processing and low-dose CBCT dental applications. A low-dose CBCT image enhancement method based on image fusion is proposed to address the need for subzygomatic small screw insertion. Specifically, firstly, a sharpening correction module is proposed, where the CBCT image is sharpened to compensate for the loss of details in the underexposed/over-exposed region. Secondly, a visibility restoration module based on type II fuzzy sets is designed, and a contrast enhancement module using curve transformation is designed. In addition to this, we propose a perceptual fusion module that fuses visibility and contrast of oral CBCT images. As a result, the problems of overexposure/underexposure, low visibility, and low contrast that occur in oral CBCT images can be effectively addressed with consistent interpretability. The proposed algorithm was analyzed in comparison experiments with a variety of algorithms, as well as ablation experiments. After analysis, compared with advanced enhancement algorithms, this algorithm achieved excellent results in low-dose CBCT enhancement and effective observation of subzygomatic small screw implantation. Compared with the best performing method, the evaluation metric is 0.07–2 higher on both datasets. The project can be found at: https://github.com/sunpeipei2024/low-dose-CBCT.

In Vivo Evaluation of Miconazole-Nitrate-Loaded Transethosomal Gel Using a Rat Model Infected with Candida albicans.

Miconazole nitrate (MCNR), an antifungal drug, is used to treat superficial infections. The objective of the current study was to assess the antifungal effectiveness of MCNR-loaded transethosomal gel (MNTG) against Candida albicans in an in vivo rat model. The outcomes were compared with those of the miconazole nitrate gel (MNG) and marketed Daktarin® cream (2%) based on histopathological and hematological studies. The results of the skin irritation test revealed the safety profile of the MNTG. The MNTG demonstrated the greatest antifungal activity in the histological analysis and the visible restoration of the skin, and the rats revealed an apparent evidence of recovery. Compared to the untreated group, the treated group's lymphocyte and white blood cells counts increased, but their eosinophil counts decreased. In conclusion, MNTG exhibited the greatest antifungal activity, which might be connected to the improved skin permeability of the transethosome's nanosized vesicles. Therefore, it could be considered a promising carrier for topical usage and the treatment of cutaneous candidiasis. More clinical research needs to be performed in order to demonstrate its effectiveness and safe usage in humans.

Visibility restoration for real-world hazy images via improved physical model and Gaussian total variation

Visibility restoration for real-world hazy images via improved physical model and Gaussian total variation

Deep Multi-Patch Hierarchical Network-based Visibility Restoration Model for Autonomous Vehicles

Deep Multi-Patch Hierarchical Network-based Visibility Restoration Model for Autonomous Vehicles

A new fast and efficient dehazing and defogging algorithm for single remote sensing images

Information about the earth’s surface is difficult to capture in remote sensing images because bad weather greatly curtails visibility and diminishes visual contrast in the images. For the purpose of military survey and aerial surveillance, these images are crucial for providing information. It is quintessential to eradicate bad weather conditions like haze and fog from remote sensing images. Recently, numerous deweathering initiatives and endeavors have been undertaken to alleviate these limitations. These contemporary deweathering approaches, however, are inadequate to recover dense haze images. This work presented a novel visibility restoration approach based on segmentation and unsharp mask guided filtering method. It consists of the following steps to restore the scene’s radiance: First, a segmentation method is employed to determine atmospheric light to quantify contrast and color. Estimation of the transmission map utilizing the dark channel prior is then performed to precisely determine the proximity between objects. The resultant output image contains halo artifacts and inconsistencies in the structure. A guided filter method based on unsharp masking is employed to optimize the transmission map in order to solve this issue. The experimental results demonstrate that the proposed indicators ensures high uniformity regarding qualitative and quantitative evaluation using six performance metrics: mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), universal image quality index (UQI), fog-aware density evaluator (FADE), dehazing algorithm index (DHQI), standard deviation (CC), and blind contrast enhancement assessment (e and r).

Functional OCT angiography reveals early retinal neurovascular dysfunction in diabetes with capillary resolution.

Altered retinal neurovascular coupling may contribute to the development and progression of diabetic retinopathy (DR) but remains highly challenging to measure due to limited resolution and field of view of the existing functional hyperemia imaging. Here, we present a novel modality of functional OCT angiography (fOCTA) that allows a 3D imaging of retinal functional hyperemia across the entire vascular tree with single-capillary resolution. In fOCTA, functional hyperemia was evoked by a flicker light stimulation, recorded by a synchronized time-lapse OCTA (i.e., 4D), and extracted precisely from each capillary segment (space) and stimulation period (time) in the OCTA time series. The high-resolution fOCTA revealed that the retinal capillaries, particularly the intermediate capillary plexus, exhibited apparent hyperemic response in normal mice, and significant functional hyperemia loss (P < 0.001) at an early stage of DR with few overt signs of retinopathy and visible restoration after aminoguanidine treatment (P < 0.05). Retinal capillary functional hyperemia has strong potential to provide sensitive biomarkers of early DR, and retinal fOCTA would provide new insights into the pathophysiology, screening and treatment of early DR.

WMCP-EM: An integrated dehazing framework for visibility restoration in single image

Adopting local patches for varying haze conditions is crucial for optimizing the performance in single image dehazing. We propose a novel two-fold method with a prime focus on self-adaptive prior named Weighted Median Channel Prior (WMCP) to resolve the problems introduced by using a fixed size local-patch in the dehazing process. WMCP works by leveraging the spatially changing haze statistics such as inclusion–exclusion of related pixels for estimating depth-map in varying haze conditions. It is a scale-invariant technique that retains most of the information present in the local neighbourhood of the hazy input image for estimating scene depth, which traditional methods generally fail to preserve. In addition, an unsharp-masking based technique called edge-modulation (EM) promotes hidden or missing details such as microscopic edges and textures lost due to haze, making this scheme beneficial in ensuring a visually aesthetic and realistic dehazed image. This research also includes a set of ablation tests to assess the contributions of each module engaged in the dehazing process. We performed a comparative evaluation of our method with several state-of-the-art techniques, revealing its superiority in terms of visibility improvement and edge preservation, especially when the dense haze regions are taken into consideration.

Unified Multi-Weather Visibility Restoration

Automated surveillance is widely opted for applications such as traffic monitoring, vehicle identification, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> . But, various weather degradation factors such as rain and snow streaks, along with atmospheric veil severely affect the perceptual quality of an image, eventually affecting the performance of these applications. There exist weather specific (rain, haze, snow, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> .) methods focusing on respective restoration task. As image restoration is a preprocessing step for high level surveillance applications, it is practically inapplicable to have different architectures for different weather restoration. In this paper, we propose a lightweight unified network, having 1.1M parameters (1 / 40 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{th}$</tex-math></inline-formula> and 1 / 6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{th}$</tex-math></inline-formula> of the existing state-of-the-art rain with veil removal, and snow with veil removal methods respectively) for removal of rain and snow along with the veiling effect present in the images. In this network, we propose two parallel streams to handle the degradations and restoration: First, degradation removal stream (DRS) focuses mainly on removing randomly repeating degradations <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.,</i> rain and snow streaks, through the proposed adaptive multi-scale feature sharing block (AMFSB) and stage-wise subtractive block (SSB). Second, feature corrector stream (FCS) mainly focuses on refining the partial outputs of the first stream, reducing the veiling effect and acts supplementary to the first stream. Finally, we leverage contrastive regularization for better convergence of the proposed network. Substantial experiments on synthetic as well as real-world images, along with extensive ablation studies, demonstrate that the proposed method performs competitively with the existing state-of-the-art methods for multi-weather image restoration. The code is available at: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><uri>https://github.com/AshutoshKulkarni4998/UVRNet</uri> </i> .

Single Image Dehazing via Fusion of Multilevel Attention Network for Vision-Based Measurement Applications

Nowadays, researchers use vision-based measurement tools to record, detect, and monitor an atmospheric phenomenon called haze. It impedes the proper functioning of many outdoor industrial systems, such as autonomous driving, surveillance, satellite imagery, etc. Conventional visibility restoration methods cannot accurately recover image quality due to inaccurate estimations of haze thickness and the presence of color-cast effects. Deep neural networks are evolving due to their ability to directly dehaze images from hazy scenes. Therefore, a unique attention-based end-to-end dehazing network named Oval-Net has been proposed in this study to restore clear images from its counterpart without employing the atmospheric scattering model. The Oval-Net is an encoder-decoder architecture that uses spatial and channel attention at each stage to focus on dominant and significant information while avoiding the transmission of irrelevant information from the encoder to the decoder, allowing quicker convergence. The proposed approach outperforms seven state-of-the-art algorithms in quantitative and qualitative assessments of a variety of synthetic and real-world hazy images, proving its effectiveness for vision-based industrial systems.

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

Haze Removal Method for Efficient Visualization of Remotely Sensed Satellite Images

Abstract: Images captured in foggy weather conditions often suffer from poor visibility, which will create a lot of impacts on the outdoor computer vision systems, such as video surveillance, intelligent transportation assistance system, remote sensing space cameras and so on. In such situations, traditional visibility restoration approaches usually cannot adequately restore images due to poor estimation of haze thickness and the persistence of color cast problems. In our work, we propose a visibility restoration approach to effectively solve inadequate haze thickness estimation and alleviate color cast problems. By doing so, a high-quality image with clear visibility and vivid color can be generated to improve the visibility of single input image (with fog or haze), as well as the image’s details. Our approach stems from two important statistical observations about haze-free images and the haze itself. First, Wavelet decomposition is applied and LUM Filter is applied on the decomposed image. Finally, we can get the dehazed output.

Visibility restoration of haze and dust image using color correction and composite channel prior

Visibility restoration of haze and dust image using color correction and composite channel prior

Polarization-based smoke removal method for surgical images.

Smoke generated during surgery affects tissue visibility and degrades image quality, affecting surgical decisions and limiting further image processing and analysis. Polarization is a fundamental property of light and polarization-resolved imaging has been studied and applied to general visibility restoration scenarios such as for smog or mist removal or in underwater environments. However, there is no related research or application for surgical smoke removal. Due to differences between surgical smoke and general haze scenarios, we propose an alternative imaging degradation model by redefining the form of the transmission parameters. The analysis of the propagation of polarized light interacting with the mixed medium of smoke and tissue is proposed to realize polarization-based smoke removal (visibility restoration). Theoretical analysis and observation of experimental data shows that the cross-polarized channel data generated by multiple scattering is less affected by smoke compared to the co-polarized channel. The polarization difference calculation for different color channels can estimate the model transmission parameters and reconstruct the image with restored visibility. Qualitative and quantitative comparison with alternative methods show that the polarization-based image smoke-removal method can effectively reduce the degradation of biomedical images caused by surgical smoke and partially restore the original degree of polarization of the samples.

Infrared Thermal Image Enhancement in Cold Spot Detection of Condenser Air Ingress

The cold spot identification approach is limited due to the lack of high-resolution infrared thermal images. To solve the problem, infrared thermal images are enhanced using several ways. To improve the thermal images for cold spot detection, researchers used CLAHE, the Canny edge detection method, and deep learning approaches based on denoising autoencoder. The comparison of several enhancement methods based on quality metric factors leads to the selection of the best method. The noise in the Infrared (IR) image is reduced by using a high-resolution autoencoder. The ability to convert a 32 × 32 infrared image to a 64 x 64 resolution image is demonstrated. This study presents an information visibility restoration technique that includes stacked Denoising Autoencoder (DAE) to improve anomalous areas in the condenser's infrared thermal images keeping in mind the current popularity of deep learning models in machine learning. The use of a deep learning autoencoder improves structural similarity index of the image, which is comprehensive. The structural similarity index of the image is improved when a deep learning autoencoder is used. In comparison to CLAHE and the Canny edge detection approach, substantial research indicates that the High-resolution autoencoder is best suited for IR image improvement. Thermal imaging, the suggested technique can improve anomalies without sacrificing crucial information when compared to the straight discriminant analysis.

Polarimetric Imaging in the Environment Containing Medium and Object

Polarimetric imaging has been studied and applied to the problem of visibility restoration in various scenarios such as haze, mist and underwater. Although studies have shown that under certain conditions, circular polarimetric imaging has certain advantages over linear polarimetric imaging, however, for a complex environment containing both scattering medium and object, the performance of linear and circular polarimetric imaging is affected by many factors. In this paper, the propagation of linear and circular polarized light in the scattering medium is theoretically analyzed, then the simulation experiments under different experimental conditions are carried out and the conclusions are summarized. In order to validate the simulation results, the measurement experiments are carried out in dynamic smoke scenarios with different smoke concentrations. The results show that, the propagation of the polarized light, especially the circular polarized light, is determined by medium conditions. Generally, both the linear and circular polarimetric imaging had an ability to reduce the image degradation caused by smoke, however, under some certain environment conditions, unlike the linear polarized channels, the difference between the orthogonal circular polarized channels may be approached or even reversed, which may limit the circular polarization-based difference imaging and visibility restoration performance.

Unpaired Image Dehazing With Physical-Guided Restoration and Depth-Guided Refinement

Most existing single image dehazing methods aim to learn supervised models from paired synthetic data, which often limits their generalization ability in real-world applications. Besides, due to ignoring the merits of physical model in visibility restoration and the properties of depth features in clarity improvement, we observe that only relying on the transfer capability of unpaired adversarial learning will suffer from low-quality recovery. To this end, we develop an effective end-to-end unpaired image dehazing method by integrating a physical-guided restoration stage and a depth-guided refinement stage in a GAN framework, named as PDR-GAN. Specifically, the dark channel prior is embedded in the restoration stage to provide constraints for the network, and the preliminary dehazed image is first generated. For the refinement stage, we excavate the potential relationship between the depth and transmission map to better refine the results of the previous stage and further recover the distant area details. Our framework benefits from the stage-wise learning strategy of model-based restoration and feature-based reconstruction, which is especially helpful for image dehazing when paired data is not available. Experimental results show that our method is superior to the current unpaired dehazing approaches in terms of both quantitative and qualitative.

Evolving Fusion-Based Visibility Restoration Model for Hazy Remote Sensing Images Using Dynamic Differential Evolution

Remote sensing images taken during poor environmental conditions are degraded by the scattering of atmospheric particles, which affects the performance of many imaging systems. Hence, an efficient visibility restoration model is required to remove haze from distorted images. However, the design of visibility restoration models is an ill-posed problem as the physical information, such as depth information and attenuation model, is usually unknown. The physical parameters computed using existing models, such as dark channel prior and gradient channel prior, are not accurate, especially for images with large haze gradients. Therefore, in this article, an evolving visibility restoration model is proposed for remote sensing images. Initially, the fusion-based transmission map is computed from the foreground and sky regions. The transmission map is further improved by designing a hybrid constraint-based variational model. Finally, a dynamic differential evolution is utilized to optimize the control parameters of the proposed model. The proposed model is validated on 50 synthetic benchmarks and 50 real-life remote sensing images. For comparative analysis, ten well-known restoration models are also considered. The comparative analysis demonstrates that the proposed model outperforms the existing restoration models.

Effect of axitinib regulating the pathological blood-brain barrier functional recovery for glioblastoma therapeutics.

AimsDysfunction of the blood–brain barrier (BBB) is a prominent pathological feature of glioblastoma (GBM). Vascular endothelial growth factor (VEGF) is confirmed to be abnormally elevated in the pathogenesis of GBM, causing BBB pathological disruption, which further allows the leakage of neurotoxic blood‐derived molecules into the central nervous system (CNS), interfering brain homeostasis and leading to poor patient outcome. Since BBB is an integral and pivotal part of the brain microenvironment, which strongly supports the occurrence and the pathological progression of GBM, here we have selected the VEGFR antagonist axitinib as a BBB functional regulator and hypothesized to regulate pathological BBB restoration for GBM effective treatment.MethodsThe pathological BBB cell model was constructed to investigate the timeliness and dose effect of axitinib regulating pathological BBB restoration. In order to investigate the efficacy and safety of axitinib regulating pathological BBB restoration for anti‐GBM treatment, the orthotropic GBM‐bearing mice model was established for in vivo study, and bioluminescent imaging was used to real‐time and noninvasively monitor tumor growth response in vivo, and survival time was also recorded.ResultsAxitinib under non‐cytotoxic dosage regulated pathological BBB restoration in a time‐dependent mode, and multiple intervention of axitinib could realize a visible restoration of pathological BBB in vitro. Moreover, axitinib treatment restored pathological BBB in orthotropic GBM‐bearing mice. We further confirmed that functional restoration of pathological BBB with axitinib had certain curative effect in prolonging median survival of orthotropic GBM‐bearing mice at non‐cytotoxic dosages in vivo.ConclusionThe mechanism of axitinib involved in BBB functional regulation in the treatment of GBM is first illuminated in this report; moreover, this is the first report first referring to regulating pathological BBB functional recovery for GBM effective therapeutics. Overall, the view of regulating pathological BBB functional recovery may offer a novel sight for other CNS diseases relating to BBB permeability effective therapeutics.