One-Pot Multi-Frame Denoising

TL;DR

This paper introduces OPD, an unsupervised multi-frame denoising method that leverages mutual supervision among noisy frames, outperforming traditional supervised and unsupervised denoising techniques in various noise scenarios.

Contribution

It proposes the first unsupervised multi-frame denoising approach, OPD, which utilizes mutual supervision among noisy frames and introduces two implementation strategies, RC and AL.

Findings

OPD achieves state-of-the-art unsupervised denoising performance.

OPD is comparable to supervised methods for Gaussian, Poisson, and OCT speckle noise.

Mutual supervision among frames enhances denoising effectiveness.

Abstract

The performance of learning-based denoising largely depends on clean supervision. However, it is difficult to obtain clean images in many scenes. On the contrary, the capture of multiple noisy frames for the same field of view is available and often natural in real life. Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training. So we propose an unsupervised learning strategy named one-pot denoising (OPD) for multi-frame images. OPD is the first proposed unsupervised multi-frame denoising (MFD) method. Different from the traditional supervision schemes including both supervised Noise2Clean (N2C) and unsupervised Noise2Noise (N2N), OPD executes mutual supervision among all of the multiple frames, which gives learning more diversity of supervision and allows models to mine deeper into the correlation among frames. N2N has also been proved to be actually a simplified case of the proposed OPD. From the perspectives of data allocation and loss function, two specific implementations, random coupling (RC) and alienation loss (AL), are respectively provided to accomplish OPD during model training. In practice, our experiments demonstrate that OPD behaves as the SOTA unsupervised denoising method and is comparable to supervised N2C methods for synthetic Gaussian and Poisson noise, and real-world optical coherence tomography (OCT) speckle noise.