not-so-BigGAN: Generating High-Fidelity Images on Small Compute with Wavelet-based Super-Resolution

Seungwook Han, Akash Srivastava, Cole Hurwitz +2

State-of-the-art models for high-resolution image generation, such as BigGAN and VQVAE-2, require an incredible amount of compute resources and/or time (512 TPU-v3 cores) to train,…