Search

Non-blind image deblurring has attracted a lot of attention in the field of low-level vision. However, the existing non-blind deblurring methods cannot effectively deal with a saturated blurry image. The key point is that the degradation model of saturated blurry images does not satisfy the linear convolution model of a conventional blurry image. To solve the problem, in this paper, we proposed a novel deep non-blind deblurring method, dubbed saturated image non-blind deblurring network(SDBNet). The SDBNet contains two trainable sub-network, i.e., confident estimate network (CEN) and detail enhance network (DEN). Specifically, the SDBNet uses CEN to estimate the confidence map for the saturated blurry image, which is used to recognize saturated pixels in the blurry image, and then uses the confidence map, and blur kernel to restore the blurry image. Finally, we use DEN to enhance the edges and textures of the restored image. We first pre-train CEN and DEN. In order to effectively pre-train CEN, we propose a new robust function, which is used to generate label data for CEN. The experimental results show that compared with several existing non-blind deblurring methods, SDBNet can effectively restore saturated blurry images and better restore the texture, edge, and other structural information of blurry images. [ABSTRACT FROM AUTHOR]

Skin is the largest organ of the human body and participates in the functional activities of the human body all the time. Therefore, human beings have a large risk of getting skin diseases. The diseased skin lesion image shows visually different characteristics from the normal skin image, and sometimes unusual skin color may indicate human viscera or autoimmune issues. However, the current recognition and classification of dermatological conditions still rely on expert visual diagnosis rather than a visual algorithm. This is because there are many kinds of lesion features of skin diseases, and the lesion accounts for a small proportion of the skin image, so it is difficult to learn the required lesion features; meanwhile, some dermatology images have too few samples to deal with the problem of small samples. In view of the above limitations, we propose a model named Lesion Area Aware Shifted windows Transformer for dermatological conditions classification rely on the powerful performance and excellent result of Swin transformer recently proposed. For brief notation, we use its abbreviation later. Our main contributions are as follows. First, we modify the Swin transformer and use it in the automatic classification of dermatological conditions. Using the self‐attention mechanism of the transformer, our method can mine more long‐distance correlations between diseased tissue image features. Using its shifting windows, we can fuse local features and global features, so it is possible to get better classification results with a flexible receptive field. Second, we use a skip connection to grasp and reinforce global features from the previous block and use Swin transformer to extract detailed local features, which will excavate and merge global features and local features further. Third, considering Swin transformer is a lightweight model compared with traditional transformers, our model is compact for deployment and more favorable to resource‐strict medical devices. [ABSTRACT FROM AUTHOR]

This paper presents a new broadband ocean bottom seismograph (OBS) developed by the SUSTech OBS lab for passive-source seafloor seismic observations. This instrument, called Pankun, has several key features that set it apart from traditional OBS instruments. In addition to the seismometer-separated scheme, these features include a unique shielding structure to minimize current-induced noise, a compact gimbal for accurate leveling, and low power consumption for extended operation on the seafloor. The design and testing of Pankun's primary components are thoroughly described in this paper. The instrument has been successfully tested in the South China Sea, demonstrating its ability to record high-quality seismic data. The anti-current shielding structure of Pankun OBS has the potential to improve low-frequency signals, particularly on the horizontal components, in seafloor seismic data. [ABSTRACT FROM AUTHOR]

The ocean‐bottom currents are believed to be largely responsible for the high noise level in ocean bottom seismograph (OBS) data, in particular on the horizontal components. Due to the lack of in‐situ experiments and measurements, the generation mechanism and characteristics of the current‐induced noise are still poorly understood. In this paper, we designed an experiment to explore the features of current‐induced noise. A sensor module from a typical passive‐source OBS was installed in a water flume that can produce controllable steady water flows. We measured and analyzed the recorded noise with changing current velocities, with and without shielding. With other noise sources, such as infragravity waves precluded, this experiment demonstrates that the currents can generate low‐frequency noise, particularly <0.1 Hz. The noise level depends on the current velocity as well as the frequency. While the current‐induced noise affects the horizontal components significantly, its impacts on the vertical component appear negligible. The experiment shows that current‐induced noise has a dominant direction approximately perpendicular to the currents, a pattern consistent with an actual OBS on the flank of Mariana Trench, where the current direction is supposed to be along the trench. Shielding the sensor module with a plastic casing can substantially suppress the noise, indicating that shielding is a practical, low‐cost scheme to reduce the current‐induced noise. Key Points: Current‐induced noise exists in a wide frequency band; its level depends on the current velocity and the frequencyCurrent‐induced noise shows a dominant direction roughly perpendicular to currents, consistent with that at an actual ocean bottom seismograph in Mariana TrenchShielding the sensor can suppress the current‐induced noise substantially [ABSTRACT FROM AUTHOR]

Natural image degradation is frequently unavoidable for various reasons, including noise, blur, compression artifacts, haze, and raindrops. The majority of previous works have advanced significantly. They, however, consider only one type of degradation and overlook hybrid degradation factors, which are fairly common in natural images. To tackle this challenge, we propose a multistage network architecture. It is capable of gradually learning and restoring the hybrid degradation model of the image. The model comprises three stages, with each pair of adjacent stages combining to exchange information between the early and late stages. Meanwhile, we employ a double-pooling channel attention block that combines maximum and average pooling. It is capable of inferring more intricate channel attention and enhancing the network's representation capability. Then, during the model training step, we introduce contrastive learning. Our method outperforms comparable methods in terms of qualitative scores and visual effects and restores more detailed textures to improve image quality. [ABSTRACT FROM AUTHOR]

Limited by the poor quality of the camera, transmission bandwidth, excessive compression and other factors, low-resolution images widely exist in our lives. Single image super-resolution method is a kind of image processing task which can obtain high-resolution image from corresponding source low-resolution image. With the development of deep learning technology, a series of deep learning methods have brought crucial improvement for SISR problem. However, we observe that no matter how deep the network structures for SISR are designed, they usually have poor performances on restoration of tiny or irregular details, we call them weak texture information. The main reason for this phenomenon is that weak texture information is not obvious relative to the salient features, so as weak texture information feature is less extracted in the process of neural network feature extraction. To address this problem, we propose a SISR method which owns unique weak texture information prediction module and call it as weak texture information map guided image super-resolution with deep residual networks. In our network structure, two auxiliary sub-networks work together to capture grab details information and predict weak texture information. Then, predicted weak texture information will be fused into main sub-network. Therefore, our network can obtain more irregular details which usually miss in deep learning based methods. Finally, both qualitative experiments and visual effects demonstrate the effectiveness of our proposed algorithm. Specifically, our method can restore more irregular image details. [ABSTRACT FROM AUTHOR]