EUVIMEDEUVIMED entdecken
Crossref

LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images

Guichen Huang, Ruoyu Wang, Xiangjun Gao, Che Sun, Yuwei Wu, Shenghua Gao, Yunde Jia

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4994-5002

DOI: 10.1609/aaai.v40i6.42504 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Guichen Huang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D Gaussian Splatting (3DGS) achieves high-fidelity novel view synthesis, but its application in online long-sequence scenarios is still restricted. Existing methods either rely on slow per-scene optimization or lack efficient frame-wise 3DGS updates, making them unsuitable for online long-sequence videos. In this paper, we propose LongSplat, an online real-time 3D Gaussian reconstruction framework designed for long-sequence image input. The core idea of LongSplat is to maintain a global 3DGS set and design a streaming 3DGS update mechanism that selectively compressing redundant historical Gaussians and introducing new Gaussians by comparing the current observations with the historical Gaussian. To achieve this goal, we design a Gaussian-Image Representation (GIR), which encodes 3D Gaussian parameters into a structured, image-like 2D format. GIR simultaneously enables identity-aware redundancy compression as well as the fusion of current view and historical Gaussians, which are used for online reconstruction and adapt the model to long sequences without overwhelming memory or computational costs. Extensive experiments demonstrate that LongSplat achieves state-of-the-art efficiency-quality trade-offs in real-time novel view synthesis, delivering real-time reconstruction while reducing Gaussian counts by 44% compared to per-pixel prediction paradigms.

Zitieren

APA

Huang, G., Wang, R., Gao, X., Sun, C., Wu, Y., Gao, S., & Jia, Y. (2026). LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4994-5002. https://doi.org/10.1609/aaai.v40i6.42504

Vancouver

Huang G, Wang R, Gao X, Sun C, Wu Y, Gao S, et al. LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4994-5002. doi:10.1609/aaai.v40i6.42504

BibTeX
@article{Huang2026,
  author = {Huang, Guichen and Wang, Ruoyu and Gao, Xiangjun and Sun, Che and Wu, Yuwei and Gao, Shenghua and Jia, Yunde},
  title = {LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {6},
  pages = {4994--5002},
  doi = {10.1609/aaai.v40i6.42504}
}
Kostenlos starten →