PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation

Abstract

show that with much less expenditure, PixelFolder obtains new state-of-the-art (SOTA) performance on two benchmark datasets, i.e., 3.77 FID and 2.45 FID on FFHQ and LSUN Church, respectively.Meanwhile, PixelFolder is also more efficient than the SOTA methods like StyleGAN2, reducing about 74% computation and 36% parameters, respectively. These results greatly validate the effectiveness of the proposed PixelFolder. Our code is available at https://github.com/BlingHe/PixelFolder.