# Noise2Kernel: Adaptive Self-Supervised Blind Denoising using a Dilated Convolutional Kernel Architecture

arXiv: https://arxiv.org/abs/2012.03623 · HTML: https://mlsanity.com/paper/2012.03623/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [As if by magic: self-supervised training of deep despeckling networks with MERLIN](https://mlsanity.com/paper/2110.13148/) (2021)
- [ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoising](https://mlsanity.com/paper/2102.09858/) (2021)
- [Joint self-supervised blind denoising and noise estimation](https://mlsanity.com/paper/2102.08023/) (2021)
- [Self-supervised Physics-based Denoising for Computed Tomography](https://mlsanity.com/paper/2211.00745/) (2022)
- [On normalization-equivariance properties of supervised and unsupervised denoising methods: a survey](https://mlsanity.com/paper/2402.15352/) (2024)
- [Decay2Distill: Leveraging spatial perturbation and regularization for self-supervised image denoising](https://mlsanity.com/paper/2208.01948/) (2022)
- [I2V: Towards Texture-Aware Self-Supervised Blind Denoising using Self-Residual Learning for Real-World Images](https://mlsanity.com/paper/2302.10523/) (2023)

## Abstract (arXiv)

With the advent of recent advances in unsupervised learning, efficient training of a deep network for image denoising without pairs of noisy and clean images has become feasible. However, most current unsupervised denoising methods are built on the assumption of zero-mean noise under the signal-independent condition. This assumption causes blind denoising techniques to suffer brightness shifting problems on images that are greatly corrupted by extreme noise such as salt-and-pepper noise. Moreover, most blind denoising methods require a random masking scheme for training to ensure the invariance of the denoising process. In this paper, we propose a dilated convolutional network that satisfies an invariant property, allowing efficient kernel-based training without random masking. We also propose an adaptive self-supervision loss to circumvent the requirement of zero-mean constraint, which is specifically effective in removing salt-and-pepper or hybrid noise where a prior knowledge of noise statistics is not readily available. We demonstrate the efficacy of the proposed method by comparing it with state-of-the-art denoising methods using various examples.