PanNet

class deepinv.models.PanNet(backbone_net=None, hrms_shape=(4, 900, 900), scale_factor=4, highpass_kernel_size=5, device='cpu', **kwargs)

Bases: Module

PanNet architecture for pan-sharpening.

PanNet neural network from Yang et al.[1].

Takes input measurements as a deepinv.utils.TensorList with elements (MS, PAN), where MS is the low-resolution multispectral image of shape (B, C, H, W) and PAN is the high-resolution panchromatic image of shape (B, 1, H*r, W*r) where r is the pan-sharpening factor.

Parameters:

• backbone_net (torch.nn.Module) – Backbone neural network, e.g. ResNet. If None, defaults to a simple ResNet.

• hrms_shape (tuple[int]) – shape of high-resolution multispectral images (C,H,W), defaults to (4,900,900)

• scale_factor (int) – pansharpening downsampling ratio HR/LR, defaults to 4

• highpass_kernel_size (int) – square kernel size for extracting high-frequency features, defaults to 5

• device (str) – torch device, defaults to “cpu”

---

References:

[1]

Junfeng Yang, Xueyang Fu, Yuwen Hu, Yue Huang, Xinghao Ding, and John Paisley. Pannet: a deep network architecture for pan-sharpening. In Proceedings of the IEEE international conference on computer vision, 5449–5457. 2017.

create_sampler(direction, hr_shape, noise_gain=0.0)

Helper function for downsampling/upsampling images (useful for reduced-resolution training with Wald’s protocol).

Parameters:

• direction (str) – down or up

• hr_shape (tuple) – HRMS input shape (C,H,W)

• noise_gain (float) – noise applied to downsampling ONLY, defaults to 0.

Return dinv.physics.Physics:

deepinv sampler

Return type:

Physics

forward(y, physics, *args, **kwargs)

Evaluate the pansharpening model

Parameters:

• y (deepinv.utils.TensorList) – (MS,PAN) images

• physics (deepinv.physics.Pansharpen) – Pansharpening operator

Examples using PanNet:

Remote sensing with satellite images

Remote sensing with satellite images