Flexible image denoising model with multi-layer conditional feature modulation

Jia-Zhi Du, Xin Qiao, Zifei Yan, Hongzhi Zhang, Wangmeng Zuo

Abstract: Highlights•We present a novel flexible denoising network with multi-layer conditional feature modulation (CFM).•The CFM achieves a better tradeoff between noise removal and detail preservation, and is applicable to other denoising networks.•The proposed CFMNet performs favorably in comparison to the state-of-the-art methods, making it highly attractive in image denoising.