计算机科学
卷积神经网络
人工智能
加性高斯白噪声
降噪
过度拟合
联营
噪音(视频)
管道(软件)
一般化
计算机视觉
模式识别(心理学)
高斯噪声
白噪声
图像(数学)
人工神经网络
数学
电信
数学分析
程序设计语言
作者
Shi Guo,Zifei Yan,Kai Zhang,Wangmeng Zuo,Lei Zhang
出处
期刊:Cornell University - arXiv
日期:2018-07-12
被引量:4
标识
DOI:10.48550/arxiv.1807.04686
摘要
While deep convolutional neural networks (CNNs) have achieved impressive success in image denoising with additive white Gaussian noise (AWGN), their performance remains limited on real-world noisy photographs. The main reason is that their learned models are easy to overfit on the simplified AWGN model which deviates severely from the complicated real-world noise model. In order to improve the generalization ability of deep CNN denoisers, we suggest training a convolutional blind denoising network (CBDNet) with more realistic noise model and real-world noisy-clean image pairs. On the one hand, both signal-dependent noise and in-camera signal processing pipeline is considered to synthesize realistic noisy images. On the other hand, real-world noisy photographs and their nearly noise-free counterparts are also included to train our CBDNet. To further provide an interactive strategy to rectify denoising result conveniently, a noise estimation subnetwork with asymmetric learning to suppress under-estimation of noise level is embedded into CBDNet. Extensive experimental results on three datasets of real-world noisy photographs clearly demonstrate the superior performance of CBDNet over state-of-the-arts in terms of quantitative metrics and visual quality. The code has been made available at https://github.com/GuoShi28/CBDNet.
科研通智能强力驱动
Strongly Powered by AbleSci AI