Search

We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN). Single-image super-resolution reconstruction technology is to reconstruct fuzzy low-resolution images into clearer high-resolution images. It is a research hotspot in the field of computer vision and image processing. In recent years, the attention mechanism has been successfully applied in image super-resolution reconstruction. However, the existing methods use the channel attention mechanism and the spatial attention mechanism separately, or simply superimpose them, which cannot effectively unify the adjustment effects of both, and the performance is limited. This paper proposes a method that can merge channel attention and spatial attention into pixel attention, which achieves more precise adjustment of feature map information. The pixel attention convolutional neural network method built on this basis can improve the quality of image texture detail reconstruction. We have been tested on five widely used standard datasets, the experimental results show that the method is superior to most current representative reconstruction methods, especially in terms of high-definition picture texture restoration. [ABSTRACT FROM AUTHOR]

Single image rain removal requires a large number of channel features and image texture in the process of rain removal. In this work, we propose a Channel Memory Network (CMN) for single-image rain removal, which is a multi-stage rain removing network structure similar to recurrent neural network. One Channel Memory Block (CMB) is also employed by CMN to extract rain streaks texture feature efficiently. CMB is able to focus on features on the channel and optionally selects useful information. In addition, Channel Attention Block (CAB) is adopted in skip connection to enhance the features from previous modules. Gated Recurrent Unit (GRU) reduces the loss in the process of parameters sharing and selectively transfers the feature to the next stage. The network structure shares a lot of parameters so that more rain streaks information can be used efficiently in the process of feature transmission. A quantity of experiments show that the performance of the proposed method is better than that of the state-of-the-art methods on five synthetic datasets. [ABSTRACT FROM AUTHOR]

Image dehazing aims to recover a clean image from a hazy image, which is a challengingly longstanding problem. In this paper, we propose an Ensemble Multi-scale Residual Attention Network (EMRA-Net) to directly generate a clean image, which include two parts: a three-scale residual attention CNN (TRA-CNN), and an ensemble attention CNN (EA-CNN). In TRA-CNN, we employ wavelet transform to obtain the downsampled images, instead of using common spatial downsampling methods, such as nearest downsampling and strided-convolution. With the help of wavelet transform, we can avoid the loss of image texture details. Moreover, in each scale-branch, Res2Net modules are connected in series to make full use of the hierarchical features from the original hazy images, and channel attention mechanism is introduced to focus channel-dimension information. Finally, an EA-CNN is proposed to fuse coarse images generated from TRA-CNN into a refined clean image. Extensive experiments on the benchmark synthetic hazy datasets and the real-world hazy dataset prove that proposed EMRA-Net is superior to previous state-of-the-art methods both in subjective visual perception and objective image quality assessment metrics. [ABSTRACT FROM AUTHOR]

Despite the rapid development of single-image super-resolution (SISR) methods of generative adversarial networks (GAN), which can reconstruct visually realistic images, the problem of high discrepancy between the recovered details or textures and the ground truth persists. To address this issue, an SISR reconstruction GAN based on a feedback and attention mechanism (FBSRGAN) is proposed. Specifically, we select a network with a feedback mechanism as the generator, which can gradually create high-resolution images through the feedback connection. The attention mechanism is combined with the feedback block to adaptively select useful feature information and effectively process the feedback stream and enhance the image output quality. We use the relative average least squares GAN loss to reduce the instability of the optimization generator process to guide GAN to obtain more realistic results. The results show that compared with the ESRGAN method, when the amplification factor is 4, PSNR and SSIM of the proposed method increase by 0.386 and 0.0141, respectively, and PI decreases by 0.284, while the number of parameters is only 18.5% of that of ESRGAN, when tested on the Set5 dataset. Compared with existing GAN-based SR methods, FBSRGAN achieves superior performance in terms of both perceptual ability and image distortion. [ABSTRACT FROM AUTHOR]