BM3D#
- class deepinv.models.BM3D[source]#
Bases:
Denoiser
BM3D denoiser.
The BM3D denoiser was introduced in “Image denoising by sparse 3D transform-domain collaborative filtering”, by Dabov et al., IEEE Transactions on Image Processing (2007).
Note
Unlike other denoisers from the library, this denoiser is applied sequentially to each noisy image in the batch (no parallelization). Furthermore, it does not support backpropagation.
Warning
This module wraps the BM3D denoiser from the BM3D python package. It can be installed with
pip install bm3d
.- forward(x, sigma, **kwargs)[source]#
Run the denoiser on image with noise level \(\sigma\).
- Parameters:
x (torch.Tensor) – noisy image
sigma (float) – noise level