SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations

arXiv:2206.14464v3 Announce Type: replace
Abstract: Score-based generative models (SGMs) show the state-of-the-art sampling quality and diversity. However, their training/sampling complexity is notoriously high due to the highly complicated forward/reverse processes, so they are not suitable for resource-limited settings. To solving this problem, learning a simpler process is gathering much attention currently. We present an enhanced GAN-based denoising method, called SPI-GAN, using our proposed straight-path interpolation definition. To this end, we propose a GAN architecture i) denoising through the straight-path and …

abstract art arxiv attention complexity cs.ai cs.lg denoising diffusion diversity gan gans generative generative models however path process processes quality sampling show state training type