AI RESEARCH
Improved DDIM Sampling with Moment Matching Gaussian Mixtures
arXiv CS.CV
•
ArXi:2311.04938v5 Announce Type: replace We propose using a Gaussian Mixture Model (GMM) as reverse transition operator (kernel) within the Denoising Diffusion Implicit Models (DDIM) framework, which is one of the most widely used approaches for accelerated sampling from pre-trained Denoising Diffusion Probabilistic Models (DDPM). Specifically we match the first and second order central moments of the DDPM forward marginals by cons