Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration
Although learning-based image restoration methods have made significant progress, they
still struggle with limited generalization to real-world scenarios due to the substantial domain
gap caused by training on synthetic data. Existing methods address this issue by improving
data synthesis pipelines, estimating degradation kernels, employing deep internal learning,
and performing domain adaptation and regularization. Previous domain adaptation methods
have sought to bridge the domain gap by learning domain-invariant knowledge in either …
still struggle with limited generalization to real-world scenarios due to the substantial domain
gap caused by training on synthetic data. Existing methods address this issue by improving
data synthesis pipelines, estimating degradation kernels, employing deep internal learning,
and performing domain adaptation and regularization. Previous domain adaptation methods
have sought to bridge the domain gap by learning domain-invariant knowledge in either …
[PDF][PDF] Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration
KLZYZ Wang, CC Loy - arXiv preprint arXiv:2406.18516, 2024 - researchgate.net
Although deep learning-based image restoration methods have made significant progress,
they still struggle with limited generalization to real-world scenarios due to the substantial
domain gap caused by training on synthetic data. Existing methods address this issue by
improving data synthesis pipelines, estimating degradation kernels, employing deep internal
learning, and performing domain adaptation and regularization. Previous domain adaptation
methods have sought to bridge the domain gap by learning domain-invariant knowledge in …
they still struggle with limited generalization to real-world scenarios due to the substantial
domain gap caused by training on synthetic data. Existing methods address this issue by
improving data synthesis pipelines, estimating degradation kernels, employing deep internal
learning, and performing domain adaptation and regularization. Previous domain adaptation
methods have sought to bridge the domain gap by learning domain-invariant knowledge in …
Showing the best results for this search. See all results