SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning

TL;DR

SimVPv2 introduces a simplified, CNN-based spatiotemporal predictive model that outperforms previous complex architectures in accuracy and efficiency across multiple datasets.

Contribution

It presents a novel streamlined architecture with Gated Spatiotemporal Attention, eliminating the need for heavy Unet-like structures, and achieves state-of-the-art results with reduced complexity.

Findings

Superior performance on Moving MNIST with fewer FLOPs

Faster training and inference times

Robust generalization across diverse datasets

Abstract

Recent years have witnessed remarkable advances in spatiotemporal predictive learning, with methods incorporating auxiliary inputs, complex neural architectures, and sophisticated training strategies. While SimVP has introduced a simpler, CNN-based baseline for this task, it still relies on heavy Unet-like architectures for spatial and temporal modeling, which still suffers from high complexity and computational overhead. In this paper, we propose SimVPv2, a streamlined model that eliminates the need for Unet architectures and demonstrates that plain stacks of convolutional layers, enhanced with an efficient Gated Spatiotemporal Attention mechanism, can deliver state-of-the-art performance. SimVPv2 not only simplifies the model architecture but also improves both performance and computational efficiency. On the standard Moving MNIST benchmark, SimVPv2 achieves superior performance compared to SimVP, with fewer FLOPs, about half the training time, and 60% faster inference efficiency. Extensive experiments across eight diverse datasets, including real-world tasks such as traffic forecasting and climate prediction, further demonstrate that SimVPv2 offers a powerful yet straightforward solution, achieving robust generalization across various spatiotemporal learning scenarios. We believe the proposed SimVPv2 can serve as a solid baseline to benefit the spatiotemporal predictive learning community.