Additionnal images for Adversarial SARDINet clarification

Here are some more images to give more context to the paper,

 

Figure A1 : Discriminator architecture used for the adversarial training of the implemented approach

 

 

          Input SAR                            Optical GT                           CycleGAN                             Pix2Pix                                    Ours                                  Adv. Scr.

Figure A2 : Results examples for an image without normalization – SAR image is displayed as (VV, 1/2 (V + VH), HH) and Optical image as RGB