Search

Underwater image enhancement presents a significant challenge due to the complex and diverse underwater environments that result in severe degradation phenomena such as light absorption, scattering, and color distortion. More importantly, obtaining paired training data for these scenarios is a challenging task, which further hinders the generalization performance of enhancement models. To address these issues, we propose a novel approach, the Hybrid Contrastive Learning Regularization (HCLR-Net). Our method is built upon a distinctive hybrid contrastive learning regularization strategy that incorporates a unique methodology for constructing negative samples. This approach enables the network to develop a more robust sample distribution. Notably, we utilize non-paired data for both positive and negative samples, with negative samples are innovatively reconstructed using local patch perturbations. This strategy overcomes the constraints of relying solely on paired data, boosting the model's potential for generalization. The HCLR-Net also incorporates an Adaptive Hybrid Attention module and a Detail Repair Branch for effective feature extraction and texture detail restoration, respectively. Comprehensive experiments demonstrate the superiority of our method, which shows substantial improvements over several state-of-the-art methods in terms of quantitative metrics, significantly enhances the visual quality of underwater images, establishing its innovative and practical applicability. Our code is available at: https://github.com/zhoujingchun03/HCLR-Net. [ABSTRACT FROM AUTHOR]

Since underwater optical imaging is affected by underwater light absorption and attenuation, the pixels of images distribute unevenly, and image structures are damaged to different degrees, leading to problems such as color distortion, low contrast, and blurred details. A single-color correction method cannot improve the contrast and details of images, and a single contrast enhancement method will cause image color distortion and local contrast over-enhanced and weak-enhanced. To deal with the problems simultaneously, this paper proposes an underwater image enhancement method based on variable contrast and saturation enhancement model and local contrast correction. Firstly, we design a white balance method based on pixel transformation to adjust the pixel distribution and further work out color distortion; Moreover, a variable contrast and saturation enhancement model is designed to recover the image structure and statistical characteristics effectively and further promote global contrast; Ultimately, contrast limited histogram equalization is adopted to perform local contrast correction, and then solve the over-enhanced and weak-enhanced. The enhancement results based on the synthetic and real underwater image data sets show that the proposed method is superior to some advanced qualitative and quantitative evaluation methods and effectively elevates visual effects. [ABSTRACT FROM AUTHOR]

Since the attenuation and absorption of light in the water medium and the influence of the tiny suspended particles, underwater images are degraded and suffer from color cast and low contrast. An underwater image enhancement method based on color correction and three-interval histogram stretching is proposed to handle these issues. Firstly, a color correction method based on sub-interval linear transformation is designed to achieve color correction. Meanwhile, using the three adaptive sub-histograms equalization algorithm to enhance the contrast, and then the resulting images of the above-mentioned methods are combined by the multi-scale fusion. Final experiments demonstrate the proposed method can improve the image contrast, obtain the details of the bright and dark regions of the image, rich color, and finally output high-quality images. [ABSTRACT FROM AUTHOR]

The color distortion and low contrast of underwater images are caused by the absorption of light by water and the scattering of suspended particles. So, we propose an underwater image restoration method based on secondary guided transmission map, which can effectively restore the color, visibility and natural appearance of underwater image. We use improved guided filter to refine the transmission map. Firstly, the rough transmission map is decomposed into the basic image and the detail image by the guided filter. And then refined transmission map is reconstructed after processing the images respectively. Finally, auto level processing is conducted on the restored image to improve the contrast of the image. In order to evaluate the effectiveness of our method, qualitative and quantitative comparisons and application test are carried out. Experimental results demonstrate that compared with several state-of-the-art methods, the proposed method can get genuine color, natural appearance, and the improvement of visibility and contrast. [ABSTRACT FROM AUTHOR]

To solve the color cast and low contrast of underwater images caused by the effects of light absorption and scattering, we propose a novel underwater image enhancement method via bi-interval histogram equalization. The proposed method consists of three main parts: color correction, contrast enhancement, and multiscale fusion. First, the color cast is eliminated by automatic white balancing. Then, homomorphic filtering is adopted to decompose the image into high-frequency information and low-frequency information, the high-frequency information is enhanced by the gradient field bi-interval equalization which enhances the contrast and details of the image, and the low-frequency information is disposed via gamma correction for adjusting the exposure. Finally, we adopt a multiscale fusion strategy to fuse the high-frequency information, high-frequency after bi-interval equalization, and low-frequency information based on contrast, saturation, and exposure. Qualitative and quantitative performance evaluations demonstrate that the proposed method can effectively enhance the details and global contrast of the image and achieve better exposedness of the dark areas, which outperforms several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Due to wavelength-dependent light absorption and scattering, underwater images often appear with a colour cast and blurry details. Most existing deep learning methods utilize a single input end-to-end network structure, which leads to a single form and content of the extracted features. To address these problems, we present a novel multi-feature underwater image enhancement method via embedded fusion mechanism (MFEF). We find that the quality of reconstruction results is affected by the quality of the input image to some extent, and use pre-processing to obtain high-quality images, which can improve the final reconstruction effect. We introduce the white balance (WB) algorithm and the contrast-limited adaptive histogram equalization (CLAHE) algorithm employing multiple path inputs to extract different forms of rich features in multiple views. To fully interact with features from multiple views, we design a multi-feature fusion (MFF) module to fuse derived image features. We suggest a novel pixel-weighted channel attention module (PCAM) that calibrates the detailed features of the degraded images using a weight matrix to give diverse weights to the encoded features. Ultimately, our network utilizes a fusion mechanism-based encoder and decoder that can be applied to restore various underwater scenes. In the UIEB dataset, our PSNR increased by 10.2% compared to that of Ucolor. Extensive experimental results demonstrate that the MFEF method outperforms other state-of-the-art underwater image enhancement methods in various real-world datasets. [ABSTRACT FROM AUTHOR]

• A novel model based on information distribution and light scattering is designed to adaptively estimate the background light. • The method only uses a single image as input. • Estimate scene depth with feature priors. • Perform extensive experiments to validate the proposed method. Underwater images suffer from blurred details, color cast, and contrast reduction, caused by absorption and scattering of light. To address these degradation issues, we propose a novel underwater image restoration method based on information distribution and light scattering prior. Concretely, we first estimate the background light according to the information distribution and light scattering characteristics of the background light area. Then, the scene depth map and transmission map are obtained by the relationship between the brightness information and color attenuation. Finally, the underwater image formation model is inversed to obtain the restored image. Extensive experiments indicate that our method can effectively remove the color cast and increase contrast. Furthermore, compared with several state-of-the-art methods, the proposed method yields better results. The qualitative and quantitative results demonstrate that our approach is superior to other comparison methods. [Display omitted] [ABSTRACT FROM AUTHOR]

The use of underwater cameras instead of divers to enter complex underwater areas for real-time monitoring of fish, shrimp, and algae is significant to the aquaculture industry. However, underwater images are severely degraded due to light absorption and scattering, limiting the development of underwater computer vision and robot vision perception. To solve blurriness and color degradation issues, this paper developed a restoration method based on backscatter pixel prior and color cast removal from the physical point of view of underwater image degradation. The proposed method used only a single underwater image as an input to estimate various parameters accurately, such as depth map, backscatter map, and illuminant map. Specifically, a backscatter estimation algorithm based on a depth map was proposed to improve the contrast of underwater images. Then, an algorithm was designed to remove color deviation based on the illuminant map. In particular, a color compensation strategy was created that could completely eliminate red artifacts in underwater images that were generated by the strong attenuation of the red channel. We designed comparative experiments from multiple angles on different real underwater image datasets. Experiments showed that the proposed method improved the contrast and removed the color deviation of light absorption compared to several reported methods. Even on underwater images with severe attenuation, the proposed method showed a significant positive effectiveness and stability on color cast removal. [ABSTRACT FROM AUTHOR]

• Underwater image is divided into five categories. • Calculate the color loss rate of RGB three channels. • Multi scene color restoration method to correct the color. • Stretch 64 multi contrast factor histograms to improve the contrast. Light is absorbed and scattered when propagating in water, which results in low quality and poor visibility of underwater optical images. Furthermore, the absorption of light by water causes color distortion, whereas the scattering of light by small particles suspended in water results in low image contrast. To enhance the underwater image quality, we developed a method based on light scattering characteristics. Firstly, we group the color cast into five categories according to the proportion of the average of the RGB channels. Then, we use the optical attenuation characteristics to calculate the color loss rate of the RGB channels of underwater images in different scenes and develop a multi-scene color restoration method to correct the color cast of underwater images. While keeping the color constant, we set a 64-block multi-contrast factor histogram stretching to enhance the contrast of the underwater image. The experimental results verify that the developed method has achieved image quality improvement via qualitative and quantitative evaluation. Our approach is proved to effectively improve the quality of underwater images with color distortion, low contrast, and detail loss. [Display omitted] [ABSTRACT FROM AUTHOR]