@Article{s22114255,
AUTHOR = {Lee, Kanggeun and Jeong, Won-Ki},
TITLE = {Noise2Kernel: Adaptive Self-Supervised Blind Denoising Using a Dilated Convolutional Kernel Architecture},
JOURNAL = {Sensors},
VOLUME = {22},
YEAR = {2022},
NUMBER = {11},
ARTICLE-NUMBER = {4255},
URL = {https://www.mdpi.com/1424-8220/22/11/4255},
ISSN = {1424-8220},
ABSTRACT = {With the advent of unsupervised learning, efficient training of a deep network for image denoising without pairs of noisy and clean images has become feasible. Most current unsupervised denoising methods are built on self-supervised loss with the assumption of zero-mean noise under the signal-independent condition, which causes brightness-shifting artifacts on unconventional noise statistics (i.e., different from commonly used noise models). Moreover, most blind denoising methods require a random masking scheme for training to ensure the invariance of the denoising process. In this study, 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 increase the tolerance for unconventional noise, which is specifically effective in removing salt-and-pepper or hybrid noise where 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.},
DOI = {10.3390/s22114255}
}