Estimating Fine-Grained Noise Model via Contrastive Learning
This addresses the challenge of generating realistic training data for image denoising across different cameras, though it is incremental as it builds on existing noise modeling and estimation trends.
The authors tackled the problem of improving real-world image denoising by combining noise modeling and estimation, proposing a pipeline that learns fine-grained noise models via contrastive learning and synthesizes realistic noisy data, achieving competitive performance with state-of-the-art methods.
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.