1. Progressive Growing of GANS
for Improved Quality, Stability,
and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen
ICLR 2018 Oral
2. Method Generate Image Disadvantages
Autoregressive
(Pixel RNN/CNN)
Sharp 1. Slow to evaluate (generate pixel by pixel)
2. Do not have a latent representation (similar to Deconv)
VAEs Blurry Information bottleneck
GANs Sharp 1. Only work on small resolutions
2. Hard to train
Motivation
3. • Higher resolution is easier to tell difference.
• Smaller batch size.
• So Grow G and D progressively
Why it is hard?
8. Pixelwise feature vector normalization in G
• After every conv layer (In G)
• It is like batch-norm but works on pixel wise
• N is the number of feature maps
• In instance-norm a-mean(a) /std(a)