Modeling sRGB Camera Noise with Normalizing Flows

TL;DR

This paper introduces a novel normalizing flows-based model for accurately capturing and synthesizing complex noise distributions in sRGB images, improving denoising performance especially for smartphone cameras with small sensors.

Contribution

The paper presents the first sRGB noise model using normalizing flows, capable of modeling complex noise distributions after ISP processing, outperforming existing raw-domain models.

Findings

Our model significantly outperforms baselines in noise modeling and synthesis.

Denoisers trained on synthetic noise from our model outperform those trained on baseline noise.

The approach effectively captures complex noise characteristics in sRGB images across various ISO levels.

Abstract

Noise modeling and reduction are fundamental tasks in low-level computer vision. They are particularly important for smartphone cameras relying on small sensors that exhibit visually noticeable noise. There has recently been renewed interest in using data-driven approaches to improve camera noise models via neural networks. These data-driven approaches target noise present in the raw-sensor image before it has been processed by the camera's image signal processor (ISP). Modeling noise in the RAW-rgb domain is useful for improving and testing the in-camera denoising algorithm; however, there are situations where the camera's ISP does not apply denoising or additional denoising is desired when the RAW-rgb domain image is no longer available. In such cases, the sensor noise propagates through the ISP to the final rendered image encoded in standard RGB (sRGB). The nonlinear steps on the ISP culminate in a significantly more complex noise distribution in the sRGB domain and existing raw-domain noise models are unable to capture the sRGB noise distribution. We propose a new sRGB-domain noise model based on normalizing flows that is capable of learning the complex noise distribution found in sRGB images under various ISO levels. Our normalizing flows-based approach outperforms other models by a large margin in noise modeling and synthesis tasks. We also show that image denoisers trained on noisy images synthesized with our noise model outperforms those trained with noise from baselines models.