Restore from Restored: Single Image Denoising with Pseudo Clean Image
This work addresses the limitation of existing denoising methods in leveraging internal image information, offering an incremental improvement for image processing applications.
The authors tackled the problem of improving image denoising by combining external and internal information, proposing a fine-tuning algorithm that adapts pre-trained networks to specific test images, resulting in enhanced performance on benchmark datasets including real noisy images.
In this study, we propose a simple and effective fine-tuning algorithm called "restore-from-restored", which can greatly enhance the performance of fully pre-trained image denoising networks. Many supervised denoising approaches can produce satisfactory results using large external training datasets. However, these methods have limitations in using internal information available in a given test image. By contrast, recent self-supervised approaches can remove noise in the input image by utilizing information from the specific test input. However, such methods show relatively lower performance on known noise types such as Gaussian noise compared to supervised methods. Thus, to combine external and internal information, we fine-tune the fully pre-trained denoiser using pseudo training set at test time. By exploiting internal self-similar patches (i.e., patch-recurrence), the baseline network can be adapted to the given specific input image. We demonstrate that our method can be easily employed on top of the state-of-the-art denoising networks and further improve the performance on numerous denoising benchmark datasets including real noisy images.