Proceedings of the AAAI Conference on Artificial Intelligence · 2020 · 120 citations · 35 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine LearningDeep LearningDigital Image ProcessingImage ProcessingImage RestorationNoiseNoise ReductionAdditive NoiseDeep Learning-based Image RestorationImage DenoisingImage Noise ReductionImpulse NoiseRandom NoiseWhite Noise
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.
35
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Kai Zhang, Wangmeng Zuo, Yunjin Chen et al. · IEEE Transactions on Image Processing · 2017 · 8.8K citations · Full text
Weighted Nuclear Norm Minimization with Application to Image Denoising
Shuhang Gu, Lei Zhang, Wangmeng Zuo et al. · 2014 · 2.3K citations
Natural Sciences, Biomedical Engineering, Computer Vision +15
Learning Deep CNN Denoiser Prior for Image Restoration
Kai Zhang, Wangmeng Zuo, Shuhang Gu et al. · 2017 · 2.1K citations · Full text