EUVIMEDEUVIMED entdecken
Crossref

Lagrangian Motion Fields for Long-Term Motion Generation

Yifei Yang, Zikai Huang, Chenshu Xu, Shengfeng He

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1171-1184

DOI: 10.1109/tpami.2025.3612380 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Yifei Yang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: Guangdong Natural Science Funds for Distinguished Young Scholars, Singapore Ministry of Education AcRF Tier 1, Lee Kong Chian Fellowships.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Long-term motion generation is a challenging task that requires producing coherent and realistic sequences over extended durations. Current methods primarily rely on framewise motion representations, which capture only static spatial details and overlook temporal dynamics. This approach leads to significant redundancy across the temporal dimension, complicating the generation of effective long-term motion. To overcome these limitations, we introduce the novel concept of Lagrangian Motion Fields, specifically designed for long-term motion generation. By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions" (analogous to superpixels). This method seamlessly integrates static spatial information with interpretable temporal dynamics, transcending the limitations of existing network architectures and motion sequence content types. Our solution is versatile and lightweight, eliminating the need for neural network preprocessing. Our approach excels in tasks such as long-term music-to-dance generation and text-to-motion generation, offering enhanced efficiency, superior generation quality, and greater diversity compared to existing methods. Additionally, the adaptability of Lagrangian Motion Fields extends to applications like infinite motion looping and fine-grained controlled motion generation, highlighting its broad utility.

Förderung

  • Guangdong Natural Science Funds for Distinguished Young Scholars
  • Singapore Ministry of Education AcRF Tier 1
  • Lee Kong Chian Fellowships

Zitieren

APA

Yang, Y., Huang, Z., Xu, C., & He, S. (2026). Lagrangian Motion Fields for Long-Term Motion Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1171-1184. https://doi.org/10.1109/tpami.2025.3612380

Vancouver

Yang Y, Huang Z, Xu C, He S. Lagrangian Motion Fields for Long-Term Motion Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1171-1184. doi:10.1109/tpami.2025.3612380

BibTeX
@article{Yang2026,
  author = {Yang, Yifei and Huang, Zikai and Xu, Chenshu and He, Shengfeng},
  title = {Lagrangian Motion Fields for Long-Term Motion Generation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {1171--1184},
  doi = {10.1109/tpami.2025.3612380}
}
Kostenlos starten →