Implicit Stacked Autoregressive Model for Video Prediction

TL;DR

This paper introduces IAM4VP, an implicit stacked autoregressive model for video prediction that combines the strengths of autoregressive and non-autoregressive methods, achieving state-of-the-art results on multiple benchmarks.

Contribution

The paper proposes a novel implicit stacked autoregressive model for video prediction that effectively balances accuracy and temporal correlation, outperforming existing methods.

Findings

Achieves state-of-the-art performance on benchmark datasets.

Effectively models long-term future frames.

Balances accuracy and temporal correlation.

Abstract

Future frame prediction has been approached through two primary methods: autoregressive and non-autoregressive. Autoregressive methods rely on the Markov assumption and can achieve high accuracy in the early stages of prediction when errors are not yet accumulated. However, their performance tends to decline as the number of time steps increases. In contrast, non-autoregressive methods can achieve relatively high performance but lack correlation between predictions for each time step. In this paper, we propose an Implicit Stacked Autoregressive Model for Video Prediction (IAM4VP), which is an implicit video prediction model that applies a stacked autoregressive method. Like non-autoregressive methods, stacked autoregressive methods use the same observed frame to estimate all future frames. However, they use their own predictions as input, similar to autoregressive methods. As the number of time steps increases, predictions are sequentially stacked in the queue. To evaluate the effectiveness of IAM4VP, we conducted experiments on three common future frame prediction benchmark datasets and weather\&climate prediction benchmark datasets. The results demonstrate that our proposed model achieves state-of-the-art performance.