GuidNoise: Single-Pair Guided Diffusion for Generalized Noise Synthesis
This addresses the costly acquisition of real-world noisy data for image denoising, offering a more practical and generalized solution for researchers and practitioners in computer vision.
The paper tackles the problem of generating realistic synthetic noisy images for training denoising models by proposing GuidNoise, a method that uses only a single noisy/clean image pair as guidance, eliminating the need for camera metadata or extensive datasets, and it improves denoising performance, especially with lightweight models and limited data.
Recent image denoising methods have leveraged generative modeling for real noise synthesis to address the costly acquisition of real-world noisy data. However, these generative models typically require camera metadata and extensive target-specific noisy-clean image pairs, often showing limited generalization between settings. In this paper, to mitigate the prerequisites, we propose a Single-Pair Guided Diffusion for generalized noise synthesis GuidNoise, which uses a single noisy/clean pair as the guidance, often easily obtained by itself within a training set. To train GuidNoise, which generates synthetic noisy images from the guidance, we introduce a guidance-aware affine feature modification (GAFM) and a noise-aware refine loss to leverage the inherent potential of diffusion models. This loss function refines the diffusion model's backward process, making the model more adept at generating realistic noise distributions. The GuidNoise synthesizes high-quality noisy images under diverse noise environments without additional metadata during both training and inference. Additionally, GuidNoise enables the efficient generation of noisy-clean image pairs at inference time, making synthetic noise readily applicable for augmenting training data. This self-augmentation significantly improves denoising performance, especially in practical scenarios with lightweight models and limited training data. The code is available at https://github.com/chjinny/GuidNoise.