Gaussian Image Denoiser Based on Deep Convolutional Sparse Coding with Attention Mechanism
Yu Jia Shi, Yingying Hua, Yige Xu, Haoran Gao, Zhenya Wang, Benchang Zheng · 2020
Image denoising is the foundation of computer vision and a classic research project of computer vision. Currently, image denoising is widely used in various fields. In order to perform image denoising more effectively, we propose a deep convolutional sparse coding based on the attention mechanism (DCSCA) denoising model. In order to identify noise and remove noise more effectively, we sparsely encode the feature map instead of encoding the original image. Our model introduces attention blocks in the network structure, which allows our model to mine the noise hidden behind complex images. Our model has the advantages of a compact network structure and does not involve complex optimization models. We did not use the traditional mean square error (MSE) as our loss function, and chose to combine the loss function L1 with ssim. Compared with the most advanced methods, our model can produce better denoising results than some of the latest methods.