SARDINet Code Available
Last October, I was glad to announce the publication of my first paper as part of my PhD studies. Indeed, SARDINet, a neural network capable to translate a SAR image containing geometrical distorsions into an optical image was published in ICIP 2022.
It demonstrated sigificant improvements with regards to the results obtained by classical adversarial translation methods and shown robustness toward radiometrical and geometrical distorsions.
You can find the paper following the link : Deep Learning of Radiometrical and Geometrical Sar Distorsions for Image Modality translations.
I am pleased here to announce that the code of SARDINet is now available on GitHub !
If you are interested in running it, testing it or even improving it, do not hesitate ! And if you have any questions with regards to the paper or the code, please send me a message !
I hope this work can be useful for you ! If so, please consider citing our work as follows :
BRALET, Antoine, ATTO, Abdourrahmane M., CHANUSSOT, Jocelyn, et al. Deep Learning of Radiometrical and Geometrical Sar Distorsions for Image Modality translations. In : 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022. p. 1766-1770.
It demonstrated sigificant improvements with regards to the results obtained by classical adversarial translation methods and shown robustness toward radiometrical and geometrical distorsions.
You can find the paper following the link : Deep Learning of Radiometrical and Geometrical Sar Distorsions for Image Modality translations.
If you are interested in running it, testing it or even improving it, do not hesitate ! And if you have any questions with regards to the paper or the code, please send me a message !
I hope this work can be useful for you ! If so, please consider citing our work as follows :
BRALET, Antoine, ATTO, Abdourrahmane M., CHANUSSOT, Jocelyn, et al. Deep Learning of Radiometrical and Geometrical Sar Distorsions for Image Modality translations. In : 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022. p. 1766-1770.