EUVIMEDEUVIMED entdecken
Crossref

On the Efficient Adaptive Streaming of 3D Gaussian Splatting Over Dynamic Networks

Yifan Wang, Mufan Liu, Qi Yang, He Huang, Le Yang, Yiling Xu

IEEE Transactions on Circuits and Systems for Video Technology · 2026-04 · 36 (4) · 4594-4608

DOI: 10.1109/tcsvt.2025.3637837 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-04. Verfasst von Yifan Wang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Fundamental Research Funds for the Central Universities of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D Gaussian Splatting (3DGS) has recently emerged as a promising representation for immersive media. Its explicit splat-based structure offers high visual quality and real-time rendering, making it particularly suitable for six degrees of freedom streaming applications. However, its deployment in practical streaming scenarios is still limited due to several key challenges such as the large data volume, and insufficient support for dynamic bitrate adaptation under fluctuating network conditions. This paper presents an efficient 3DGS streaming framework that operates directly on pre-generated 3DGS models without retraining or fine-tuning. First, a training-free perceptual pruning method, which removes visually redundant Gaussians according to the human visual system metrics, is introduced. The resulting 3DGS is then encoded into a compact representation using the extended 3D codecs, exploiting its point-based structure. Next, we build a scene-specific bitrate ladder through analyzing the trade-off between resolution, bitrate, and perceptual quality. This enables efficient and fine-grained representation selection. Finally, a progressive streaming mechanism is developed. It is driven by a reinforcement learning scheduler that adaptively decides whether to download new content or enhance previously buffered content based on real-time network feedback. Experiments on real-world 3DGS datasets and bandwidth traces show that the proposed method evidently improves the quality of experience and streaming efficiency in various network scenarios.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Fundamental Research Funds for the Central Universities of China

Zitieren

APA

Wang, Y., Liu, M., Yang, Q., Huang, H., Yang, L., & Xu, Y. (2026). On the Efficient Adaptive Streaming of 3D Gaussian Splatting Over Dynamic Networks. IEEE Transactions on Circuits and Systems for Video Technology, 36(4), 4594-4608. https://doi.org/10.1109/tcsvt.2025.3637837

Vancouver

Wang Y, Liu M, Yang Q, Huang H, Yang L, Xu Y. On the Efficient Adaptive Streaming of 3D Gaussian Splatting Over Dynamic Networks. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(4):4594-4608. doi:10.1109/tcsvt.2025.3637837

BibTeX
@article{Wang2026,
  author = {Wang, Yifan and Liu, Mufan and Yang, Qi and Huang, He and Yang, Le and Xu, Yiling},
  title = {On the Efficient Adaptive Streaming of 3D Gaussian Splatting Over Dynamic Networks},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {4},
  pages = {4594--4608},
  doi = {10.1109/tcsvt.2025.3637837}
}
Kostenlos starten →