EUVIMEDEUVIMED entdecken
Crossref

DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction

Lianqiang Gan, Junyu Lai, Jingze Ju, Lianli Gao, Yi Bin

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (3) · 3059-3067

DOI: 10.1609/aaai.v39i3.32314 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Lianqiang Gan und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Videos inherently contain complex temporal dynamics across various spatial directions, often entangled in ways that obscure effective dynamic extraction. Previous studies typically process video spatiotemporal features without disentangling, which hampers their ability to extract dynamic information. Additionally, the extraction of dynamics is disrupted by transient high-dynamic information in video sequences, e.g., noise or flicker, which has received limited attention in the literature. To tackle those problems, this paper proposes the Disentangling and Filtering Dynamics Network (DFDNet). Firstly, to disentangle the interwoven dynamics, DFDNet decomposes the spatially encoded video sequences into lower dimensional sequences. Secondly, a learnable threshold filter is proposed to eliminate the transient high-dynamic information. Thirdly, the model incorporates an MLP to extract the temporal dependencies from the disentangled and filtered sequences. DFDNet demonstrates competitive performance across four chosen datasets, including both low and high-resolution videos. Specifically, on the low-resolution Moving MNIST dataset, DFDNet achieves a 19% improvement on MSE over the previous state-of-the-art model. On the high-resolution SJTU4K dataset, it outperforms the previous state-of-the-art model by 10% on the LPIPS metric under similar inference time.

Zitieren

APA

Gan, L., Lai, J., Ju, J., Gao, L., & Bin, Y. (2025). DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(3), 3059-3067. https://doi.org/10.1609/aaai.v39i3.32314

Vancouver

Gan L, Lai J, Ju J, Gao L, Bin Y. DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(3):3059-3067. doi:10.1609/aaai.v39i3.32314

BibTeX
@article{Gan2025,
  author = {Gan, Lianqiang and Lai, Junyu and Ju, Jingze and Gao, Lianli and Bin, Yi},
  title = {DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {3059--3067},
  doi = {10.1609/aaai.v39i3.32314}
}
Kostenlos starten →