Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
This work is significant for researchers and practitioners in image denoising, as it provides a more generalizable and applicable method for synthesizing realistic noisy images, overcoming the limitations of metadata dependency.
The paper addresses the challenge of generating realistic noisy sRGB images without relying on camera metadata. They propose Prompt-Driven Noise Generation (PNG), a framework that learns high-dimensional prompt features from real-world input noise to synthesize diverse and realistic noisy images. The generated images are successfully applied to real-world noise removal across various benchmark datasets.
Denoising in the sRGB image space is challenging due to noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by the scarcity of real noisy-clean image pairs, which are expensive and difficult to collect. To address this limitation, several generative methods have been developed to synthesize realistic noisy images from limited data. These generative approaches often rely on camera metadata during both training and testing to synthesize real-world noise. However, the lack of metadata or inconsistencies between devices restricts their usability. Therefore, we propose a novel framework called Prompt-Driven Noise Generation (PNG). This model is capable of acquiring high-dimensional prompt features that capture the characteristics of real-world input noise and creating a variety of realistic noisy images consistent with the distribution of the input noise. By eliminating the dependency on explicit camera metadata, our approach significantly enhances the generalizability and applicability of noise synthesis. Comprehensive experiments reveal that our model effectively produces realistic noisy images and show the successful application of these generated images in removing real-world noise across various benchmark datasets.