Can I read State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend on EtoBox?

State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend by Cui, Fei; Fang, Jiaojiao; Wu, Xiaojiang; Lai, Zelong; Yang, Mengke; Jia, Menghan; Liu, Guizhong is a scholarly article available to read on EtoBox.

What is State-space Decomposition Model for Video Prediction Considering Long-term Motion Trend about?

Stochastic video prediction enables the consideration of uncertainty in future motion, thereby providing a better reflection of the dynamic nature of the environment. Stochastic video prediction methods based on image auto-regressive recurrent models need to feed their predictions back into the latent space. Conversely, the state-space models, which decouple frame synthesis and temporal prediction, proves to be more efficient. However, inferring long-term temporal information about motion and generalizing to dynamic scenarios under non-stationary assumptions remains an unresolved challenge. In this paper, we propose a state-space decomposition stochastic video prediction model that decomposes the overall video frame generation into deterministic appearance prediction and stochastic motion prediction. Through adaptive decomposition, the model's generalization capability to dynamic scenarios is enhanced. In the context of motion prediction, obtaining a prior on the long-term trend of future motion is crucial. Thus, in the stochastic motion prediction branch, we infer the long-term motion trend from conditional frames to guide the generation of future frames that exhibit high consiste

Author

Cui, Fei; Fang, Jiaojiao; Wu, Xiaojiang; Lai, Zelong; Yang, Mengke; Jia, Menghan; Liu, Guizhong

Published

2024

Language

EN