With its significant performance improvements, the deep learning paradigm has
become a standard tool for modern image denoisers. While promising performance
has been shown on seen noise distributions, existing approaches often suffer
from generalisation to unseen noise types or general and real noise. It is
understandable as the model is designed to learn paired mapping (e.g. from a
noisy image to its clean version). In this paper, we instead propose to learn
to disentangle the noisy image, under the intuitive assumption that different
corrupted versions of the same clean image share a common latent space. A
self-supervised learning framework is proposed to achieve the goal, without
looking at the latent clean image. By taking two different corrupted versions
of the same image as input, the proposed Multi-view Self-supervised
Disentanglement (MeD) approach learns to disentangle the latent clean features
from the corruptions and recover the clean image consequently. Extensive
experimental analysis on both synthetic and real noise shows the superiority of
the proposed method over prior self-supervised approaches, especially on unseen
novel noise types. On real noise, the proposed method even outperforms its
supervised counterparts by over 3 dB.

通过多角度自监督解缠方法 (MeD)，本文在合成噪声和真实噪声的实验分析中展现了该方法在未见过的新噪声类型上相对于之前的自监督方法的卓越性能。在真实噪声上，该方法的性能甚至超过了其监督对照组超过 3 dB。

多视角自监督解缠结通用图像降噪

Multi-view Self-supervised Disentanglement for General Image Denoising

Discriminative learning-based image denoisers have achieved promising
performance on synthetic noises such as Additive White Gaussian Noise (AWGN).
The synthetic noises adopted in most previous work are pixel-independent, but
real noises are mostly spatially/channel-correlated and
spatially/channel-variant. This domain gap yields unsatisfied performance on
images with real noises if the model is only trained with AWGN. In this paper,
we propose a novel approach to boost the performance of a real image denoiser
which is trained only with synthetic pixel-independent noise data dominated by
AWGN. First, we train a deep model that consists of a noise estimator and a
denoiser with mixed AWGN and Random Value Impulse Noise (RVIN). We then
investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained
model to real noises. Extensive experiments demonstrate the effectiveness and
generalization of the proposed approach. Notably, our method achieves
state-of-the-art performance on real sRGB images in the DND benchmark among
models trained with synthetic noises. Codes are available at
this https URL

本文提出了一种使用 Pixel-shuffle Down-sampling 策略的新方法，该方法通过训练一个深度模型（由噪声估计器和去噪器组成）使用混合的 AWGN 和 RVIN 数据，从而提高使用合成独立像素噪声数据训练的实际图像去噪器返回结果的效果和泛化性能，并在 DND 基准测试的实际 sRGB 图像中取得了最先进的性能。