The method uses Smooth ℓ1 loss, divergence regularization, and input optimization in DIP to prevent overfitting and achieve better denoising on real HSIs with Gaussian, sparse, and stripe noise than prior DIP variants.
A comprehensive review of hyper- spectral image denoising techniques in remote sensing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
The method uses Smooth ℓ1 loss, divergence regularization, and input optimization in DIP to prevent overfitting and achieve better denoising on real HSIs with Gaussian, sparse, and stripe noise than prior DIP variants.