I want to create realistic like license plates, I write a code to create them but they are not very realistic, for this I want to model mapping between real license plates and fake ones and then map fake license plates to convert them to realistic images.
My fake license plate:
And this is its correspondence in real world:
I want to find a suitable mapping that convert fake LPs to real one, but as you can see the mapping is not just spatial (I cannot model it just by a homography transformation). How could I model this kind of mapping?
Perfect task for GAN networks. Check this project for example CycleGAN .
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.