Estimating Fine-Grained Noise Model via Contrastive Learning

TL;DR

This paper introduces a contrastive learning-based approach to estimate fine-grained noise models for realistic image denoising, enabling camera-specific noise modeling without calibration data and improving denoising performance.

Contribution

It proposes a novel noise model estimation pipeline combining contrastive learning and noise synthesis, capable of predicting camera-specific noise models from testing images alone.

Findings

Achieves competitive denoising performance with state-of-the-art methods.

Enables noise model estimation for unknown sensors without calibration data.

Extends to multiple sensors by calibrating noise models across devices.

Abstract

Image denoising has achieved unprecedented progress as great efforts have been made to exploit effective deep denoisers. To improve the denoising performance in realworld, two typical solutions are used in recent trends: devising better noise models for the synthesis of more realistic training data, and estimating noise level function to guide non-blind denoisers. In this work, we combine both noise modeling and estimation, and propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation. Specifically, our model learns a noise estimation model with fine-grained statistical noise model in a contrastive manner. Then, we use the estimated noise parameters to model camera-specific noise distribution, and synthesize realistic noisy training data. The most striking thing for our work is that by calibrating noise models of several sensors, our model can be extended to predict other cameras. In other words, we can estimate cameraspecific noise models for unknown sensors with only testing images, without laborious calibration frames or paired noisy/clean data. The proposed pipeline endows deep denoisers with competitive performances with state-of-the-art real noise modeling methods.