Paper
Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning
Authors
Jaekyun Ko, Dongjin Kim, Soomin Lee, Guanghui Wang, Tae Hyun Kim
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.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.04870v1</id>\n <title>Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learning</title>\n <updated>2026-03-05T06:54:38Z</updated>\n <link href='https://arxiv.org/abs/2603.04870v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.04870v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>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.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n <published>2026-03-05T06:54:38Z</published>\n <arxiv:comment>CVPR 2026</arxiv:comment>\n <arxiv:primary_category term='cs.CV'/>\n <author>\n <name>Jaekyun Ko</name>\n </author>\n <author>\n <name>Dongjin Kim</name>\n </author>\n <author>\n <name>Soomin Lee</name>\n </author>\n <author>\n <name>Guanghui Wang</name>\n </author>\n <author>\n <name>Tae Hyun Kim</name>\n </author>\n </entry>"
}