Blind Universal Bayesian Image Denoising with Gaussian Noise Level Learning
arXiv:1907.03029 · doi:10.1109/TIP.2020.2976814
Abstract
Blind and universal image denoising consists of using a unique model that denoises images with any level of noise. It is especially practical as noise levels do not need to be known when the model is developed or at test time. We propose a theoretically-grounded blind and universal deep learning image denoiser for additive Gaussian noise removal. Our network is based on an optimal denoising solution, which we call fusion denoising. It is derived theoretically with a Gaussian image prior assumption. Synthetic experiments show our network's generalization strength to unseen additive noise levels. We also adapt the fusion denoising network architecture for image denoising on real images. Our approach improves real-world grayscale additive image denoising PSNR results for training noise levels and further on noise levels not seen during training. It also improves state-of-the-art color image denoising performance on every single noise level, by an average of 0.1dB, whether trained on or not.
arXiv commentFinal uncompressed TIP version available online in open access (DOI attached)
References in corpus (5)
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- Sketch-based Manga Retrieval using Manga109 Dataset
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
- Class-Aware Fully-Convolutional Gaussian and Poisson Denoising
Cited by in corpus (6)
- WINNet: Wavelet-inspired Invertible Network for Image Denoising
- Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
- PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples
- Fully Adaptive Bayesian Algorithm for Data Analysis, FABADA
- Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks
- A Self-Attention-Driven Deep Denoiser Model for Real Time Lung Sound Denoising in Noisy Environments