Noise2NoiseFlow: Realistic Camera Noise Modeling without Clean Images
Ali Maleky, Shayan Kousha, Michael S. Brown, Marcus A. Brubaker

TL;DR
This paper introduces Noise2NoiseFlow, a novel framework for realistic camera noise modeling and denoising that learns from pairs of noisy images without requiring clean images, outperforming previous models.
Contribution
It presents a joint training framework for noise modeling and denoising using only noisy image pairs, eliminating the need for clean ground-truth images.
Findings
Outperforms previous signal-processing noise models in synthesis and density estimation.
Achieves denoising results comparable to supervised methods.
Joint training significantly improves denoising performance.
Abstract
Image noise modeling is a long-standing problem with many applications in computer vision. Early attempts that propose simple models, such as signal-independent additive white Gaussian noise or the heteroscedastic Gaussian noise model (a.k.a., camera noise level function) are not sufficient to learn the complex behavior of the camera sensor noise. Recently, more complex learning-based models have been proposed that yield better results in noise synthesis and downstream tasks, such as denoising. However, their dependence on supervised data (i.e., paired clean images) is a limiting factor given the challenges in producing ground-truth images. This paper proposes a framework for training a noise model and a denoiser simultaneously while relying only on pairs of noisy images rather than noisy/clean paired image data. We apply this framework to the training of the Noise Flow architecture.…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage and Signal Denoising Methods · Image Processing Techniques and Applications · Optical measurement and interference techniques
