Asymmetric Mask Scheme for Self-Supervised Real Image Denoising
This work addresses a bottleneck in image restoration for researchers and practitioners by improving denoising performance with a novel training and inference approach.
The paper tackles the performance limitations of self-supervised denoising methods by proposing an asymmetric mask scheme that eliminates blind spot operations, achieving state-of-the-art results on real noisy image datasets.
In recent years, self-supervised denoising methods have gained significant success and become critically important in the field of image restoration. Among them, the blind spot network based methods are the most typical type and have attracted the attentions of a large number of researchers. Although the introduction of blind spot operations can prevent identity mapping from noise to noise, it imposes stringent requirements on the receptive fields in the network design, thereby limiting overall performance. To address this challenge, we propose a single mask scheme for self-supervised denoising training, which eliminates the need for blind spot operation and thereby removes constraints on the network structure design. Furthermore, to achieve denoising across entire image during inference, we propose a multi-mask scheme. Our method, featuring the asymmetric mask scheme in training and inference, achieves state-of-the-art performance on existing real noisy image datasets. All the source code will be made available to the public.