Skip to yearly menu bar Skip to main content


ExtDM: Distribution Extrapolation Diffusion Model for Video Prediction

Zhicheng Zhang · Junyao Hu · Wentao Cheng · Danda Paudel · Jufeng Yang

Arch 4A-E Poster #454
[ ] [ Project Page ]
Thu 20 Jun 5 p.m. PDT — 6:30 p.m. PDT


Video prediction is a challenging task due to its nature of uncertainty, especially for forecasting a long period. To model the temporal dynamics, advanced methods benefit from the recent success of diffusion models, and repeatedly refine the predicted future frames with 3D spatiotemporal U-Net. However, there exists a gap between the present and future and the repeated usage of U-Net brings a heavy computation burden. To address this, we propose a diffusion-based video prediction method that predicts future frames by extrapolating the present distribution of features, namely ExtDM. Specifically, our method consists of three components: (i) a motion autoencoder conducts a bijection transformation between video frames and motion cues; (ii) a layered distribution adaptor module extrapolates the present features in the guidance of Gaussian distribution; (iii) a 3D U-Net architecture specialized for jointly fusing guidance and features among the temporal dimension by spatiotemporal-window attention. Extensive experiments on five popular benchmarks covering short- and long-term video prediction verify the effectiveness of ExtDM.

Live content is unavailable. Log in and register to view live content