When AWGN-based Denoiser Meets Real Noises
This addresses the problem of poor real-world denoising performance for researchers and practitioners in image processing, though it is incremental as it builds on existing synthetic training methods.
The paper tackles the performance gap between denoisers trained on synthetic pixel-independent noise (like AWGN) and real-world spatially/channel-correlated noise, proposing a method that combines AWGN and RVIN training with pixel-shuffle down-sampling to adapt to real noises, achieving state-of-the-art results on the DND benchmark for models trained with synthetic data.
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.