EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion

Yongjia Ma, Junlin Chen, Donglin Di, Qi Xie, Lei Fan, Wei Chen, Na Zhao, Xun Yang

ACM Transactions on Multimedia Computing, Communications, and Applications · 31.07.2026 · 22 (7) · 1-25

DOI: 10.1145/3794855 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Multimedia Computing, Communications, and Applications, online erschienen am 24.06.2026. Verfasst von Yongjia Ma und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Creating high-fidelity, coherent long videos is a sought-after aspiration. While recent video diffusion models have shown promising potential, they still grapple with spatiotemporal inconsistencies and high computational resource demands. We propose Global-Local Collaborative Diffusion (GLC-Diffusion), a tuning-free method for long video generation. It models the long video denoising process by establishing denoising trajectories through Global-Local Collaborative Denoising (GLCD) to ensure overall content consistency and temporal coherence between frames. Additionally, we introduce a Noise Reinitialization strategy which combines local noise shuffling with frequency fusion to improve global content consistency and visual diversity. Further, we propose a Video Motion Consistency Refinement (VMCR) module that computes the gradient of pixel-wise and frequency-wise losses to enhance visual consistency and temporal smoothness. Extensive experiments, including quantitative and qualitative evaluations on videos of varying lengths (e.g., 3× and 6× longer), demonstrate that our method effectively integrates with existing video diffusion models, producing coherent, high-fidelity long videos superior to previous approaches.

Zitieren

APA

Ma, Y., Chen, J., Di, D., Xie, Q., Fan, L., Chen, W., Zhao, N., & Yang, X. (2026). Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion. ACM Transactions on Multimedia Computing, Communications, and Applications, 22(7), 1-25. https://doi.org/10.1145/3794855

Vancouver

Ma Y, Chen J, Di D, Xie Q, Fan L, Chen W, et al. Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion. ACM Transactions on Multimedia Computing, Communications, and Applications. 2026;22(7):1-25. doi:10.1145/3794855

BibTeX
@article{Ma2026,
  author = {Ma, Yongjia and Chen, Junlin and Di, Donglin and Xie, Qi and Fan, Lei and Chen, Wei and Zhao, Na and Yang, Xun},
  title = {Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion},
  journal = {ACM Transactions on Multimedia Computing, Communications, and Applications},
  year = {2026},
  volume = {22},
  number = {7},
  pages = {1--25},
  doi = {10.1145/3794855}
}
Kostenlos starten →