Gated Texture CNN for Efficient and Configurable Image Denoising
This addresses image denoising for applications requiring texture preservation, offering an efficient and configurable solution, though it is incremental as it builds on existing CNN-based denoising methods.
The paper tackles the problem of image denoising where existing CNN methods often remove high-frequency textures, and proposes a gated texture CNN (GTCNN) that achieves state-of-the-art performance with 4.8 times fewer parameters and allows interactive texture control without extra costs.
Convolutional neural network (CNN)-based image denoising methods typically estimate the noise component contained in a noisy input image and restore a clean image by subtracting the estimated noise from the input. However, previous denoising methods tend to remove high-frequency information (e.g., textures) from the input. It caused by intermediate feature maps of CNN contains texture information. A straightforward approach to this problem is stacking numerous layers, which leads to a high computational cost. To achieve high performance and computational efficiency, we propose a gated texture CNN (GTCNN), which is designed to carefully exclude the texture information from each intermediate feature map of the CNN by incorporating gating mechanisms. Our GTCNN achieves state-of-the-art performance with 4.8 times fewer parameters than previous state-of-the-art methods. Furthermore, the GTCNN allows us to interactively control the texture strength in the output image without any additional modules, training, or computational costs.