Abstract:Spatiotemporal predictive learning aims to forecast future frames from historical observations in an unsupervised manner, and is critical to a wide range of applications. The key challenge is to model long-range dynamics while preserving high-frequency details for sharp multi-step predictions. Existing efficient recurrent-free frameworks typically rely on strided convolutions or pooling for sampling, which tends to discard textures and boundaries, while purely spatial operators often struggle to balance local interactions with global propagation. To address these issues, we propose WaveSFNet, an efficient framework that unifies a wavelet-based codec with a spatial--frequency dual-domain gated spatiotemporal translator. The wavelet-based codec preserves high-frequency subband cues during downsampling and reconstruction. Meanwhile, the translator first injects adjacent-frame differences to explicitly enhance dynamic information, and then performs dual-domain gated fusion between large-kernel spatial local modeling and frequency-domain global modulation, together with gated channel interaction for cross-channel feature exchange. Extensive experiments demonstrate that WaveSFNet achieves competitive prediction accuracy on Moving MNIST, TaxiBJ, and WeatherBench, while maintaining low computational complexity. Our code is available at this https URL.
| Comments: | Accepted to IJCNN 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2603.23284 [cs.CV] |
| (or arXiv:2603.23284v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2603.23284 arXiv-issued DOI via DataCite |
From: Xinyong Cai [view email]
[v1]
Tue, 24 Mar 2026 14:48:59 UTC (718 KB)
[v2]
Thu, 16 Apr 2026 07:24:40 UTC (717 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。