WaveletDictDenoiser
- class deepinv.models.WaveletDictDenoiser(level=3, list_wv=['db8', 'db4'], max_iter=10, non_linearity='soft', wvdim=2, device='cpu')[source]
Bases:
Module
Overcomplete Wavelet denoising with the \(\ell_1\) norm.
This denoiser is defined as the solution to the optimization problem:
\[\underset{x}{\arg\min} \; \|x-y\|^2 + \lambda \|\Psi x\|_n\]where \(\Psi\) is an overcomplete wavelet transform, composed of 2 or more wavelets, i.e., \(\Psi=[\Psi_1,\Psi_2,\dots,\Psi_L]\), \(\lambda>0\) is a hyperparameter, and where \(\|\cdot\|_n\) is either the \(\ell_1\) norm (
non_linearity="soft"
), the \(\ell_0\) norm (non_linearity="hard"
) or a variant of the \(\ell_0\) norm (non_linearity="topk"
) where only the top-k coefficients are kept; seedeepinv.models.WaveletDenoiser()
for more details.The solution is not available in closed-form, thus the denoiser runs an optimization algorithm for each test image.
- Parameters:
level (int) – decomposition level of the wavelet transform.
wv (list[str]) – list of mother wavelets. The names of the wavelets can be found in here. (default: [“db8”, “db4”]).
device (str) – cpu or gpu.
max_iter (int) – number of iterations of the optimization algorithm (default: 10).
non_linearity (str) – “soft”, “hard” or “topk” thresholding (default: “soft”)
- forward(y, ths=0.1)[source]
Run the model on a noisy image.
- Parameters:
y (torch.Tensor) – noisy image.
ths (float, torch.Tensor) – noise level.