MFN: Metadata-Free Real-World Noisy Image Generation
Lists
Only you see this
Abstract
Real-world noise poses a significant challenge in signal processing, especially for denoising tasks. Although end-to-end denoising approaches have achieved exceptional performance, they are constrained to scenarios with abundant noisy-clean image pairs, which can be technically challenging and resource-intensive to collect. To address this issue, several generative methods have been developed to synthesize realistic noisy images from limited real-world datasets. While prior studies require camera metadata during training or testing to handle various real-world noise, the absence of metadata or variations in the information across different capturing devices is common in real-world scenarios, such as medical or microscope imaging, which limits their applicability. Thus, we aim to eliminate the need for explicit camera-related labels in both stages, enhancing applicability in real-world scenarios. To achieve this, we propose a novel framework called the Metadata-Free Noise Model (MFN), which extracts prompt features that encode input noise characteristics and generates diverse noisy images that adhere to the distribution of the input noise. Extensive experimental results demonstrate the superior performance of our model in real-world noise generation and denoising across various benchmark datasets.
BibTeX
@misc{ko2025mfn,
author = {Jaekyun Ko and Dongjin Kim and Guanghui Wang and Tae Hyun Kim},
title = {{MFN: Metadata-Free Real-World Noisy Image Generation}},
year = {2025},
url = {https://openreview.net/forum?id=sVbFE6xz82},
howpublished = {OpenReview},
note = {Submitted to ICLR 2025},
}