SimVP: Simpler yet Better Video Prediction

From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. We admire these progresses but are confused about the necessity: is there a simple method that can perform comparably well? This paper proposes SimVP, a simple video prediction model that is completely built upon CNN and trained by MSE loss in an end-to-end fashion. Without introducing any additional tricks and complicated strategies, we can achieve state-of-the-art performance on five benchmark datasets. Through extended experiments, we demonstrate that SimVP has strong generalization and extensibility on real-world datasets. The significant reduction of training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to stimulate the further development of video prediction.

Automated summary

This paper proposes SimVP, a simple and efficient video prediction model that is built upon CNN and trained by MSE loss. Despite its simplicity, SimVP achieves state-of-the-art performance on multiple benchmark datasets. Extended experiments demonstrate its strong generalization and scalability, with significantly reduced training cost.