计算机科学
概率逻辑
自回归模型
人工智能
帧(网络)
统计模型
机器学习
数学
统计
电信
作者
Ruihan Yang,Prakhar Srivastava,Stephan Mandt
出处
期刊:Entropy
[MDPI AG]
日期:2023-10-20
卷期号:25 (10): 1469-1469
被引量:8
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI