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

2026-03-05

AI Summary

Real-world image denoising in the sRGB space is hindered by the complex diversity of real noise and the scarcity of paired training data, leading to poor generalization of models in practical scenarios. To address this, this work proposes a Prompt-Driven Noise Generation (PNG) framework that synthesizes realistic, cross-device noise without relying on camera metadata. By leveraging a diffusion model architecture augmented with prompt-driven noise representation learning, PNG captures high-dimensional prompt features that encode input noise characteristics, enabling faithful reproduction of real noise distributions from limited authentic samples. Experimental results demonstrate that the generated noisy images exhibit high visual fidelity and significantly enhance both the performance and generalization capability of state-of-the-art real-image denoising models across multiple benchmarks.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

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.

Problem

• sRGB denoising
• real noise generation
• camera metadata
• noise variability
• noisy-clean image pairs

Innovation

• prompt-driven
• noise generation
• diffusion model
• real noise synthesis
• metadata-free