eduzhai > Applied Sciences > Engineering >

An Inter- and Intra-Band Loss for Pansharpening Convolutional Neural Networks

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 4 pages

Abstract: Pansharpening aims to fuse panchromatic and multispectral images from thesatellite to generate images with both high spatial and spectral resolution.With the successful applications of deep learning in the computer vision field,a lot of scholars have proposed many convolutional neural networks (CNNs) tosolve the pansharpening task. These pansharpening networks focused on variousdistinctive structures of CNNs, and most of them are trained by L2 loss betweenfused images and simulated desired multispectral images. However, L2 loss isdesigned to directly minimize the difference of spectral information of eachband, which does not consider the inter-band relations in the training process.In this letter, we propose a novel inter- and intra-band (IIB) loss to overcomethe drawback of original L2 loss. Our proposed IIB loss can effectivelypreserve both inter- and intra-band relations and can be directly applied todifferent pansharpening CNNs.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×