TY - GEN
T1 - Multispectral Style Distances and Application to Texture Synthesis Using RGB Convolutional Neural Networks
AU - Ollivier, Selim
AU - Gousseau, Yann
AU - Lefebvre, Sidonie
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/1
Y1 - 2024/1/1
N2 - State-of-the-art methods for RGB texture synthesis and style transfer leverage the representations learned by convolutional neural networks (CNN) on large datasets. Style distances, obtained by comparing statistics of deep features, play a pivotal role in synthesis procedures. Extending these distances to multispectral images is challenging because the pre-trained CNN only operate on RGB images. This work presents two multispectral style distances that still rely on a RGB CNN to avoid additional training. The first consists in a classical style distance, averaged over images formed by triplets of spectral bands. The second takes advantage of a projection of the multispectral pixels onto a three-dimensional space. We demonstrate their efficiency by performing multispectral texture synthesis.
AB - State-of-the-art methods for RGB texture synthesis and style transfer leverage the representations learned by convolutional neural networks (CNN) on large datasets. Style distances, obtained by comparing statistics of deep features, play a pivotal role in synthesis procedures. Extending these distances to multispectral images is challenging because the pre-trained CNN only operate on RGB images. This work presents two multispectral style distances that still rely on a RGB CNN to avoid additional training. The first consists in a classical style distance, averaged over images formed by triplets of spectral bands. The second takes advantage of a projection of the multispectral pixels onto a three-dimensional space. We demonstrate their efficiency by performing multispectral texture synthesis.
KW - Style distance
KW - convolutional neural networks
KW - deep learning
KW - multispectral imaging
KW - texture synthesis
UR - https://www.scopus.com/pages/publications/86000240704
U2 - 10.1109/WHISPERS65427.2024.10876488
DO - 10.1109/WHISPERS65427.2024.10876488
M3 - Conference contribution
AN - SCOPUS:86000240704
T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
BT - 2024 14th Workshop on Hyperspectral Imaging and Signal Processing
PB - IEEE Computer Society
T2 - 14th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing, WHISPERS 2024
Y2 - 9 December 2024 through 11 December 2024
ER -