When AWGN-based Denoiser Meets Real Noises

Abstract

Discriminative learning-based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). The synthetic noises adopted in most previous work are pixel-independent, but real noises are mostly spatially/channel-correlated and spatially/channel-variant. This domain gap yields unsatisfied performance on images with real noises if the model is only trained with AWGN. In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN. First, we train a deep model that consists of a noise estimator and a denoiser with mixed AWGN and Random Value Impulse Noise (RVIN). We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. Extensive experiments demonstrate the effectiveness and generalization of the proposed approach. Notably, our method achieves state-of-the-art performance on real sRGB images in the DND benchmark among models trained with synthetic noises. Codes are available at https://github.com/yzhouas/PD-Denoising-pytorch.

Accepted by AAAI 2020

References in corpus (12)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Deep Image Prior
• External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising
• Learning Deep CNN Denoiser Prior for Image Restoration
• Path-Restore: Learning Network Path Selection for Image Restoration
• Toward Convolutional Blind Denoising of Real Photographs
• Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising
• When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
• Connecting Image Denoising and High-Level Vision Tasks via Deep Learning
• DN-ResNet: Efficient Deep Residual Network for Image Denoising
• Class-specific Poisson denoising by patch-based importance sampling

Cited by in corpus (10)

• Joint Face Image Restoration and Frontalization for Recognition
• NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
• Image Restoration for Under-Display Camera
• Spatial-Adaptive Network for Single Image Denoising
• UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results
• CNN Acceleration by Low-rank Approximation with Quantized Factors
• Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
• Practical Deep Raw Image Denoising on Mobile Devices
• GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
• Convolutional versus Self-Organized Operational Neural Networks for Real-World Blind Image Denoising