TL;DR
This paper introduces a novel unpaired image denoising method that leverages a flow-based generative model trained on clean images to improve denoising performance without requiring paired noisy-clean datasets.
Contribution
It presents a new approach combining flow-based generative modeling with denoising, enabling training without paired datasets and utilizing available clean images more effectively.
Findings
Outperforms existing unsupervised denoising methods in experiments
Effectively leverages clean images to improve denoising quality
Demonstrates robustness across different noise levels
Abstract
Deep learning approaches in image processing predominantly resort to supervised learning. A majority of methods for image denoising are no exception to this rule and hence demand pairs of noisy and corresponding clean images. Only recently has there been the emergence of methods such as Noise2Void, where a deep neural network learns to denoise solely from noisy images. However, when clean images that do not directly correspond to any of the noisy images are actually available, there is room for improvement as these clean images contain useful information that fully unsupervised methods do not exploit. In this paper, we propose a method for image denoising in this setting. First, we use a flow-based generative model to learn a prior from clean images. We then use it to train a denoising network without the need for any clean targets. We demonstrate the efficacy of our method through…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
