NM-FlowGAN: Modeling sRGB Noise with a Hybrid Approach based on Normalizing Flows and Generative Adversarial Networks

arXiv:2312.10112v2 Announce Type: replace-cross
Abstract: Modeling and synthesizing real sRGB noise is crucial for various low-level vision tasks, such as building datasets for training image denoising systems. The distribution of real sRGB noise is highly complex and affected by a multitude of factors, making its accurate modeling extremely challenging. Therefore, recent studies have proposed methods that employ data-driven generative models, such as generative adversarial networks (GAN) and Normalizing Flows. These studies achieve more accurate modeling of sRGB noise compared to …

adversarial arxiv cs.cv cs.lg eess.iv generative generative adversarial networks hybrid hybrid approach modeling networks noise type