DewaterNet: A fusion adversarial real underwater image enhancement network

Underwater image enhancement algorithms have attracted much attention in underwater vision task. However, these algorithms are mainly evaluated on different datasets and metrics. In this paper, we utilize an effective and public underwater benchmark dataset including diverse underwater degradation scenes to enlarge the test scale and propose a fusion adversarial network for enhancing real underwater images. Meanwhile, the multiple inputs and well-designed multi-term adversarial loss can not only introduce multiple input image features, but also balance the impact of multi-term loss functions. The proposed network tested on the benchmark dataset achieves better or comparable performance than the other state-of-the-art methods in terms of qualitative and quantitative evaluations. Moreover, the ablation study experimentally validates the contributions of each component and hyper-parameter setting of loss functions.     

Diving deeper into underwater image enhancement: A survey

The powerful representation capacity of deep learning has made it inevitable for the underwater image enhancement community to employ its potential. The exploration of deep underwater image enhancement networks is increasing over time; hence, a comprehensive survey is the need of the hour. In this paper, our main aim is two-fold, (1): to provide a comprehensive and in-depth survey of the deep learning-based underwater image enhancement, which covers various perspectives ranging from algorithms to open issues, and (2): to conduct a qualitative and quantitative comparison of the deep algorithms on diverse datasets to serve as a benchmark, which has been barely explored before.We first introduce the underwater image formation models, which are the base of training data synthesis and design of deep networks, and also helpful for understanding the process of underwater image degradation. Then, we review deep underwater image enhancement algorithms, and a glimpse of some of the aspects of the current networks is presented, including architecture, parameters, training data, loss function, and training configurations. We also summarize the evaluation metrics and underwater image datasets. Following that, a systematically experimental comparison is carried out to analyze the robustness and effectiveness of deep algorithms. Meanwhile, we point out the shortcomings of current benchmark datasets and evaluation metrics. Finally, we discuss several unsolved open issues and suggest possible research directions. We hope that all efforts done in this paper might serve as a comprehensive reference for future research and call for the development of deep learning-based underwater image enhancement.     

基于预检机制的偏振图像去烟研究

烟的存在会导致图像目标信息的损减或丢失。针对烟在场景中具有局域性,提出了基于目标检测Yolov3算法的去烟预检机制,即在去烟流程中增加预检机制实现对烟图定向去烟,提升去烟效率和避免对无烟区的影响。不同于现有针对可见光图像的基于深度学习去雾方法,该方法将四幅偏振态图像作为网络输入,并利用多尺度注意力对抗网络提取烟区目标的偏振态特征信息,从而缓解失真现象以及丰富去烟后目标的结构和细节信息。在真实数据集上的定性与定量实验结果表明,本文提出的算法有效提升了偏振图像的去烟效果和去烟效率。     

Adaptive adversarial prototyping network for few-shot prototypical translation

Translating multiple real-world source images to a single prototypical image is a challenging problem. Notably, these source images belong to unseen categories that did not exist during model training. We address this problem by proposing an adaptive adversarial prototype network (AAPN) and enhancing existing one-shot classification techniques. To overcome the limitations that traditional works cannot extract samples from novel categories, our method tends to solve the image translation task of unseen categories through a meta-learner. We train the model in an adversarial learning manner and introduce a style encoder to guide the model with an initial target style. The encoded style latent code enhances the performance of the network with conditional target style images. The AAPN outperforms the state-of-the-art methods in one-shot classification of brand logo dataset and achieves the competitive accuracy in the traffic sign dataset. Additionally, our model improves the visual quality of the reconstructed prototypes in unseen categories. Based on the qualitative and quantitative analysis, the effectiveness of our model for few-shot classification and generation is demonstrated.     

Color correction and restoration based on multi-scale recursive network for underwater optical image

Underwater image processing has played an important role in various fields such as submarine terrain scanning, submarine communication cable laying, underwater vehicles, underwater search and rescue. However, there are many difficulties in the process of acquiring underwater images. Specifically, the water body will selectively absorb part of the light when light travels through the water, resulting in color degradation of underwater images. At the same time, due to the influence of floating substances in the water, the light has a certain degree of scattering, which will bring serious problems such as blurred details and low contrast to underwater images. Therefore, using image processing technology to restore the real appearance of underwater images has a high practical value. In order to solve the above problems, we combine the color correction method with the deblurring network to improve the quality of underwater images in this paper. Firstly, aiming at the problem of insufficient number and diversity of underwater image samples, a network combined with depth image reconstruction and underwater image generation is proposed to simulate underwater images based on the style transfer method. Secondly, for the problem of color distortion, we propose a dynamic threshold color correction method based on image global information combined with the loss law of light propagation in water. Finally, in order to solve the problem of image blurring caused by scattering and further improve the overall image clarity, the color-corrected image is reconstructed by a multi-scale recursive convolutional neural network. Experiment results show that we can obtain images closer to underwater style with shorter training time. Compared with several latest underwater image processing methods, the proposed method has obvious advantages in multiple underwater scenes. Simultaneously, we can restore the color information, remove blurring and boost detail for underwater images.     

A novel dark channel prior guided variational framework for underwater image restoration

Image captured underwater often suffers from low contrast, color distortion and noise problems, which is caused by absorbing and scattering before the light reaches the camera when traveling through water. Underwater image enhancement and restoration from a single image is known to be an ill-posed problem. To overcome these limitations, we establish an underwater total variation (UTV) model relying on underwater dark channel prior (UDCP), in which UDCP is used to estimate the transmission map. We design the data item and smooth item of the unified variational model based on the underwater image formation model. We further employ the alternating direction method of multipliers (ADMM) to accelerate the solving procedure. Numerical experiential results demonstrate that our underwater variational method obtains a good outcome on dehazing and denoising. Furthermore, compared with several other state-of-the-art algorithms, the proposed approach achieves better visual quality, which is illustrated by examples and statistics.     

Impulsive noise detection by second-order differential image and noise removal using adaptive nearest neighbourhood filter

A novel impulsive noise detection method based on the principle that the difference between the noisy pixel and the nearest good pixel will be different from the difference between two nearby good pixels. This is achieved by constructing a second-order differential image. Three new noise removal methods are presented. Simulated results show that the proposed filter gives far better results than many existing filters and is comparable to the results obtained by JM filter based on Jarque-Bera test. Our noise detection method is computationally simpler.     

基于特征解耦的无监督水下图像增强

水介质的吸收和散射特性致使水下图像存在不同类型的失真,严重影响后续处理的准确性和有效性。目前有监督学习的水下图像增强方法依靠合成的水下配对图像集进行训练,然而由于合成的数据可能无法准确地模拟水下成像的基本物理机制,所以监督学习的方法很难应用于实际的应用场景。该文提出一种基于特征解耦的无监督水下图像增强方法,一方面,考虑获取同一场景下的清晰-非清晰配对数据集难度大且成本高,提出采用循环生成对抗网络将水下图像增强问题转换成风格迁移问题,实现无监督学习;另一方面,结合特征解耦方法分别提取图像的风格特征和结构特征,保证增强前后图像的结构一致性。实验结果表明,该方法可以在非配对数据训练的情况下,能够有效恢复水下图像的颜色和纹理细节。     

散斑噪声污染的激光水下图像滤波算法

水是一种特殊的介质，在激光水下图像中总存在因水的后向散射引起的散斑噪声。充分利用形态学的不同结构多元方向形态滤波的多分辨率特性，以及形态学运算固有的能将大量的复杂图像处理运算转换为基本的逻辑与移位运算的组合来完成的特点，提出了一种多方向的形态滤波算法。不仅有效地抑制了因海水后向散射引起的散斑噪声，同时保留了激光水下目标图像的几何结构细节特征，实验表明这是一种有效的滤除水下激光图像散斑噪声的快速滤波算法。     

Cross-domain representation learning by domain-migration generative adversarial network for sketch based image retrieval

Sketch based image retrieval (SBIR), which uses free-hand sketches to search the images containing similar objects/scenes, is attracting more and more attentions as sketches could be got more easily with the development of touch devices. However, this task is difficult as the huge differences between sketches and images. In this paper, we propose a cross-domain representation learning framework to reduce these differences for SBIR. This framework aims to transfer sketches to images with the information learned both in the sketch domain and image domain by the proposed domain migration generative adversarial network (DMGAN). Furthermore, to reduce the representation gap between the generated images and natural images, a similarity learning network (SLN) is also proposed with the new designed loss function incorporating semantic information. Extensive experiments have been done from different aspects, including comparison with state-of-the-art methods. The results show that the proposed DMGAN and SLN really work for SBIR.     

Joint strong edge and multi-stream adaptive fusion network for non-uniform image deblurring

Non-uniform motion deblurring has been a challenging problem in the field of computer vision. Currently, deep learning-based deblurring methods have made promising achievements. In this paper, we propose a new joint strong edge and multi-stream adaptive fusion network to achieve non-uniform motion deblurring. The edge map and the blurred map are jointly used as network inputs and Edge Extraction Network (EEN) guides the Deblurring Network (DN) for image recovery and to complement the important edge information. The Multi-stream Adaptive Fusion Module (MAFM) adaptively fuses the edge information and features from the encoder and decoder to reduce feature redundancy to avoid image artifacts. Furthermore, the Dense Attention Feature Extraction Module (DAFEM) is designed to focus on the severely blurred regions of blurry images to obtain important recovery information. In addition, an edge loss function is added to measure the difference of edge features between the generated and clear images to further recover the edges of the deblurred images. Experiments show that our method outperforms currently public methods in terms of PSNR, SSIM and VIF, and generates images with less blur and sharper edges.     

Single underwater image haze removal with a learning-based approach to blurriness estimation

Underwater images are usually degraded due to light scattering and absorption. To recover the scene radiance of degraded underwater images, a new haze removal method is presented by incorporating a learning-based approach to blurriness estimation with the image formation model. Firstly, the image blurriness is estimated with a linear model trained on a set of selected grayscale images, the average Gaussian images and blurriness images. With the estimated image blurriness, three intermediate background lights (BLs) are computed to obtain the synthesized BL. Then the scene depth is calculated by using the estimated image blurriness and BL to construct a transmission map and restore the scene radiance. Compared with other haze removal methods, haze in degraded underwater images can be removed more accurately with our proposed method. Moreover, visual inspection, quantitative evaluation and application test demonstrate that our method is superior to the compared methods and beneficial to high-level vision tasks.     

Underwater image enhancement based on conditional generative adversarial network

Underwater images play an essential role in acquiring and understanding underwater information. High-quality underwater images can guarantee the reliability of underwater intelligent systems. Unfortunately, underwater images are characterized by low contrast, color casts, blurring, low light, and uneven illumination, which severely affects the perception and processing of underwater information. To improve the quality of acquired underwater images, numerous methods have been proposed, particularly with the emergence of deep learning technologies. However, the performance of underwater image enhancement methods is still unsatisfactory due to lacking sufficient training data and effective network structures. In this paper, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear underwater image is achieved by a multi-scale generator. Besides, we employ a dual discriminator to grab local and global semantic information, which enforces the generated results by the multi-scale generator realistic and natural. Experiments on real-world and synthetic underwater images demonstrate that the proposed method performs favorable against the state-of-the-art underwater image enhancement methods.     

Speckle noise removal based on structural convolutional neural networks with feature fusion for medical image

Application of convolutional neural networks (CNNs) for image additive white Gaussian noise (AWGN) removal has attracted considerable attentions with the rapid development of deep learning in recent years. However, the work of image multiplicative speckle noise removal is rarely done. Moreover, most of the existing speckle noise removal algorithms are based on traditional methods with human priori knowledge, which means that the parameters of the algorithms need to be set manually. Nowadays, deep learning methods show clear advantages on image feature extraction. Multiplicative speckle noise is very common in real life images, especially in medical images. In this paper, a novel neural network structure is proposed to recover noisy images with speckle noise. Our proposed method mainly consists of three subnetworks. One network is rough clean image estimate subnetwork. Another is subnetwork of noise estimation. The last one is an information fusion network based on U-Net and several convolutional layers. Different from the existing speckle denoising model based on the statistics of images, the proposed network model can handle speckle denoising of different noise levels with an end-to-end trainable model. Extensive experimental results on several test datasets clearly demonstrate the superior performance of our proposed network over state-of-the-arts in terms of quantitative metrics and visual quality.     

基于深度卷积神经网络的红外图像行人检测

红外图像中的行人检测一直是计算机视觉领域的研究热点与难点。针对传统的红外行人检测方法需要人工设计目标表达特征的弊端,本文从深度学习的角度出发,提出一种可以自动构建目标表达特征的红外行人检测卷积神经网络。在对卷积神经网络的实现原理进行分析的基础上,设计了红外行人检测卷积神经网络的初始结构,然后通过实验对初始结构进行调整,得到最终的检测神经网络。对实拍红外人体数据库进行行人检测的实验结果表明,该方法在保持低虚警率的同时可以对红外图像中的行人进行稳健检测,优于传统方法。     

Depth-aware total variation regularization for underwater image dehazing

Underwater images often show severe quality degradation due to the light absorption and scattering effects in water medium. This paper introduces a scene depth regularized underwater image dehazing method to obtain high-quality underwater images. Unlike previous underwater image dehazing methods that usually calculate a transmission map or a scene depth map using priors, we construct an exponential relationship between transmission map and normalized scene depth map. An initial scene depth is first estimated by the difference between color channels. Then it is refined by total variation regularization to keep structures while smoothing excessive details. An alternating direction algorithm is given to solve the optimization problem. Extensive experiments demonstrate that the proposed method can effectively improve the visual quality of degraded underwater images, and yields high-quality results comparative to the state-of-the-art underwater image enhancement methods quantitatively and qualitatively.     

Similar neighbor criterion for impulse noise removal in images

In this paper, a new method is proposed for removing and restoring random-valued impulse noise in images. This approach is based on a similar neighbor criterion, in which any pixel to be considered as an original pixel it should have sufficient numbers of similar neighboring pixels in a set of filtering windows. Compared with other well known methods in the literature, this technique achieves superior performance in restoring heavily corrupted noisy images. Furthermore, it has low computational complexity, and equally effective in restoring corrupted color and gray-level images.