SVNR: Spatially-variant Noise Removal with Denoising Diffusion
This addresses the challenge of realistic noise removal in images, which is important for applications like photography and medical imaging, but it is incremental as it adapts existing diffusion models.
The paper tackles the problem of applying denoising diffusion models to realistic noise removal by proposing SVNR, a novel formulation that assumes spatially-variant noise, enabling the use of the noisy input image as a starting point and achieving advantages over strong baselines and state-of-the-art methods.
Denoising diffusion models have recently shown impressive results in generative tasks. By learning powerful priors from huge collections of training images, such models are able to gradually modify complete noise to a clean natural image via a sequence of small denoising steps, seemingly making them well-suited for single image denoising. However, effectively applying denoising diffusion models to removal of realistic noise is more challenging than it may seem, since their formulation is based on additive white Gaussian noise, unlike noise in real-world images. In this work, we present SVNR, a novel formulation of denoising diffusion that assumes a more realistic, spatially-variant noise model. SVNR enables using the noisy input image as the starting point for the denoising diffusion process, in addition to conditioning the process on it. To this end, we adapt the diffusion process to allow each pixel to have its own time embedding, and propose training and inference schemes that support spatially-varying time maps. Our formulation also accounts for the correlation that exists between the condition image and the samples along the modified diffusion process. In our experiments we demonstrate the advantages of our approach over a strong diffusion model baseline, as well as over a state-of-the-art single image denoising method.