Cargando…
Noise2Kernel: Adaptive Self-Supervised Blind Denoising Using a Dilated Convolutional Kernel Architecture
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-indepe...
| Autores principales: | , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
MDPI
2022
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9185435/ https://www.ncbi.nlm.nih.gov/pubmed/35684882 http://dx.doi.org/10.3390/s22114255 |