A fast denoising fusion network using internal and external priors

As a preprocessing module, denoising can affect the overall image processing; thus, image denoising algorithms are of high significance for image processing and have been studied for several decades. Theoretically, the performances of existing algorithms can be significantly improved, but these improvements are indeed slowing down. To significantly improve the denoising performance, we propose a denoising network method called the fast denoising fusion network (FDFNet). It combines the advantages of a neural network based on block matching and 3D filtering (BM3D-Net) and a fast and flexible denoising convolutional neural network (FFDNet), which simultaneously utilizes internal and external priors to remove noise in a given image; thus, it is a fast and efficient denoising method that delivers superior performance. BM3D-Net and FFDNet can generate two images as basic estimates for fusion. We adopt a combination model to receive the two estimates, which can fuse them effectively to obtain a latent image. Through testing on standard datasets, our experimental results reveal that FDFNet outperformed state-of-the-art denoising methods in terms of both subjective and objective quality. By implementing the entire method on a CNN, the proposed method could exploit the GPU to achieve a higher efficiency. Because the proposed method combines internal and external priors effectively, it could utilize complementary prior knowledge to derive more information.