Journal
ENTROPY
Volume 25, Issue 10, Pages -Publisher
MDPI
DOI: 10.3390/e25101469
Keywords
diffusion models; deep generative models; video generation; autoregressive models
Categories
Ask authors/readers for more resources
Denoising diffusion probabilistic models are a promising new class of generative models that demonstrate high-quality image generation. This paper presents an autoregressive, end-to-end optimized video diffusion model that surpasses previous methods in perceptual and probabilistic forecasting metrics. Results show significant improvements in perceptual quality and probabilistic frame forecasting ability for various datasets.
Denoising diffusion probabilistic models are a promising new class of generative models that mark a milestone in high-quality image generation. This paper showcases their ability to sequentially generate video, surpassing prior methods in perceptual and probabilistic forecasting metrics. We propose an autoregressive, end-to-end optimized video diffusion model inspired by recent advances in neural video compression. The model successively generates future frames by correcting a deterministic next-frame prediction using a stochastic residual generated by an inverse diffusion process. We compare this approach against six baselines on four datasets involving natural and simulation-based videos. We find significant improvements in terms of perceptual quality and probabilistic frame forecasting ability for all datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available