Boosting Diffusion Models with Moving Average Sampling in Frequency Domain

arXiv:2403.17870v1 Announce Type: new
Abstract: Diffusion models have recently brought a powerful revolution in image generation. Despite showing impressive generative capabilities, most of these models rely on the current sample to denoise the next one, possibly resulting in denoising instability. In this paper, we reinterpret the iterative denoising process as model optimization and leverage a moving average mechanism to ensemble all the prior samples. Instead of simply applying moving average to the denoised samples at different timesteps, we first map …

abstract arxiv boosting capabilities cs.cv cs.mm current denoising diffusion diffusion models domain generative image image generation iterative moving next paper process sample sampling type