Toward Convolutional Blind Denoising of Real Photographs

Abstract

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.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Multi-level Wavelet-CNN for Image Restoration
• Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior
• Chaining Identity Mapping Modules for Image Denoising

Cited by in corpus (5)

• When AWGN-based Denoiser Meets Real Noises
• A relic sketch extraction framework based on detail-aware hierarchical deep network
• DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder
• High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation
• An Integrated Enhancement Solution for 24-hour Colorful Imaging