Masked Image Training for Generalizable Deep Image Denoising
This addresses a critical problem for image processing applications where noise varies, though it appears incremental as it builds on existing deep learning methods.
The paper tackles the lack of generalization in deep image denoising models, which often fail on unseen noise distributions, by introducing masked training that involves masking random pixels and features during training, resulting in improved generalization ability applicable to real-world scenarios.
When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method for image denoising, especially with the emergence of Transformer-based models that have achieved notable state-of-the-art results on various image tasks. However, deep learning-based methods often suffer from a lack of generalization ability. For example, deep models trained on Gaussian noise may perform poorly when tested on other noise distributions. To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training. Our method involves masking random pixels of the input image and reconstructing the missing information during training. We also mask out the features in the self-attention layers to avoid the impact of training-testing inconsistency. Our approach exhibits better generalization ability than other deep learning models and is directly applicable to real-world scenarios. Additionally, our interpretability analysis demonstrates the superiority of our method.