Cascaded and Recursive ConvNets (CRCNN): An effective and flexible approach for image denoising
作者：
Highlights：
• The proposed CRCNN framework deals with various noise levels and spatially variant noises.
• A total noise loss function is proposed to generalize the denoising task and preserve fine details in restored images.
• The noise level mismatch is effectively handled using the Hybrid Orthogonal Projection and Estimation (HOPE) framework.
• We prove that the recursive denoising can leverage a deblurring process in order to improve the image quality.
• The CRCNN achieves better results on both synthetic and real-world noisy images compared to the state-of-the-art methods.
摘要
•The proposed CRCNN framework deals with various noise levels and spatially variant noises.•A total noise loss function is proposed to generalize the denoising task and preserve fine details in restored images.•The noise level mismatch is effectively handled using the Hybrid Orthogonal Projection and Estimation (HOPE) framework.•We prove that the recursive denoising can leverage a deblurring process in order to improve the image quality.•The CRCNN achieves better results on both synthetic and real-world noisy images compared to the state-of-the-art methods.
论文关键词：Image denoising,Spatial variant noise,Hybrid orthogonal regularization,Convolutional neural networks
论文评审过程：Received 29 October 2019, Revised 8 April 2021, Accepted 10 August 2021, Available online 17 August 2021, Version of Record 26 August 2021.
论文官网地址：https://doi.org/10.1016/j.image.2021.116420
