CODEWITHSUNDEEP
generative-adversarial-network
rID133
rID133

Reputation: 163

how to modify GAN to work well on larger image sizes

I am working with the Image to Image GAN architecture presented by Isola et al. https://arxiv.org/abs/1611.07004

Their architecture was used on images of 256x256x3. I tried training with 512x512x3 images but my results are not as good as with my test using their smaller resolution. In particular, it seems that small details seem to be missing from what the GAN generates. It also quickly reaches a failure mode where the generator starts degrading (from my reading this is probably caused by the discriminator not being powerful enough to discern a difference so the generator starts learning random effects). Are there any general rules for adapting the architecture for larger resolution input? Also how to change the architecture to better generate small (high frequency) details? Or if anyone has links to papers showing GANs generating lots of detail.

Upvotes: 0

Views: 632

Answers (1)

coderina
coderina

Reputation: 1746

Use progressive gans (PCGANs) for outputting the larger resolution images.

Upvotes: 1

Related Questions