Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning

TL;DR

This paper introduces a prompt-driven framework for generating realistic sRGB noise images without relying on camera metadata, improving noise synthesis and denoising in real-world scenarios.

Contribution

The proposed PNG model captures real-world noise characteristics using high-dimensional prompts, eliminating the need for camera metadata and enhancing noise synthesis generalizability.

Findings

Effectively produces realistic noisy images for various datasets.

Improves denoising performance using generated noisy images.

Enhances noise synthesis without camera metadata dependency.

Abstract

Denoising in the sRGB image space is challenging due to large 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 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.