search

jhoffman / cycada_release

Code to accompany ICML 2018 paper
BSD 2-Clause "Simplified" License
561 stars 126 forks source link

Image-level adaptation from synthetic domain to real scenarios #30

Open jianingwangind opened 5 years ago

jianingwangind commented 5 years ago

First of all, thanks for the great work. Recently i have implemented an image-level adaptation from CARLA(a simulator) to real urban scenarios using cycle_gan_model.py. But the results are suboptimal since lots of detail information are losing durting the translation. clear_noon_00001435_fake_B The dataset is quite unbalanced with 9000 synthetic images and 21100 real images. The resolution differs also severely where 792 x 272 for synthetic and 4096 x 1024 for real ones. Do you have any ideas how can i get an improvement?

Thanks a lot.

lucafei commented 4 years ago

hi, i'm also recently doing a similar work. can you pls tell me how to improve the tranlation?