NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis
This addresses the problem of denoising images with unknown noise types and intensities for computer vision applications, offering an adaptive solution that extends existing denoisers.
The paper tackles image denoising for complex, unknown noise mixtures by proposing a gradual strategy that iteratively detects and removes dominating noise with tailored denoisers, achieving state-of-the-art performance on blind denoising tasks.
Fully supervised deep-learning based denoisers are currently the most performing image denoising solutions. However, they require clean reference images. When the target noise is complex, e.g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are limited by the difficulty to build a suited training set for the problem. This paper proposes a gradual denoising strategy that iteratively detects the dominating noise in an image, and removes it using a tailored denoiser. The method is shown to keep up with state of the art blind denoisers on mixture noises. Moreover, noise analysis is demonstrated to guide denoisers efficiently not only on noise type, but also on noise intensity. The method provides an insight on the nature of the encountered noise, and it makes it possible to extend an existing denoiser with new noise nature. This feature makes the method adaptive to varied denoising cases.