In order to obtain clear images and solve the problems of low image quality caused by noise disturbance,a lot of researches have been done on image denoising techniques.In the theoretical system of algorithms studied ...In order to obtain clear images and solve the problems of low image quality caused by noise disturbance,a lot of researches have been done on image denoising techniques.In the theoretical system of algorithms studied so far,many algorithms can effectively remove noise in low-dimensional images,but at the same time,the results are slightly inferior when processing high-dimensional images.This paper proposes a q-GAN,which uses multi-scale in generating networks.The convolution kernel extracts image features and transforms the denoising problem into the feature domain.In the feature domain,a residual structure is used to denoise,and the noise distribution is removed from the feature distribution.There are residual noise features in the obtained denoising features,which are removed by subsequent feature filtering of the network structure,and finally a denoised image is generated by fusing the noiseless features.展开更多
文摘In order to obtain clear images and solve the problems of low image quality caused by noise disturbance,a lot of researches have been done on image denoising techniques.In the theoretical system of algorithms studied so far,many algorithms can effectively remove noise in low-dimensional images,but at the same time,the results are slightly inferior when processing high-dimensional images.This paper proposes a q-GAN,which uses multi-scale in generating networks.The convolution kernel extracts image features and transforms the denoising problem into the feature domain.In the feature domain,a residual structure is used to denoise,and the noise distribution is removed from the feature distribution.There are residual noise features in the obtained denoising features,which are removed by subsequent feature filtering of the network structure,and finally a denoised image is generated by fusing the noiseless features.
