plenoptic.process.normalized_laplacian_pyramid

plenoptic.process.normalized_laplacian_pyramid(img)

Compute the normalized Laplacian Pyramid using pre-optimized parameters.

Model parameters are those used in Laparra et al., 2016 [10], copied from the matlab code used in the paper, found online [11].

Parameters:

img (Tensor) – Image, or batch of images of shape (batch, channel, height, width). This representation is designed for grayscale images and will be computed separately for each channel (so channels are treated in the same way as batches).

Return type:

list[Tensor]

Returns:

normalized_laplacian_activations – The normalized Laplacian Pyramid with six scales.

References

[10]

Laparra, V., Ballé, J., Berardino, A. and Simoncelli, E.P., 2016. Perceptual image quality assessment using a normalized Laplacian pyramid. Electronic Imaging, 2016(16), pp.1-6.

[11]

matlab code: https://www.cns.nyu.edu/~lcv/NLPyr/NLP_dist.m

Examples

>>> import plenoptic as po
>>> img = po.data.einstein()
>>> pyramid = po.process.normalized_laplacian_pyramid(img)
>>> [p.shape for p in pyramid]
[torch.Size([1, 1, 256, 256]),
 torch.Size([1, 1, 128, 128]),
 torch.Size([1, 1, 64, 64]),
 torch.Size([1, 1, 32, 32]),
 torch.Size([1, 1, 16, 16]),
 torch.Size([1, 1, 8, 8])]
>>> po.plot.imshow(pyramid, col_wrap=3)
<PyrFigure size ...>

(png, hires.png, pdf)