EUVIMEDEUVIMED entdecken
Crossref

4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction

Woong Oh Cho, In Cho, Seoha Kim, Jeongmin Bae, Youngjung Uh, Seon Joo Kim

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3363-3371

DOI: 10.1609/aaai.v40i5.37332 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Woong Oh Cho und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling dynamic scenes through 4D Gaussians offers high visual fidelity and fast rendering speeds, but comes with significant storage overhead. Recent approaches mitigate this cost by aggressively reducing the number of Gaussians. However, this inevitably removes Gaussians essential for high-quality rendering, leading to severe degradation in dynamic regions. In this paper, we introduce a novel 4D anchor-based framework that tackles the storage cost in different perspective. Rather than reducing the number of Gaussians, our method retains a sufficient quantity to accurately model dynamic contents, while compressing them into compact, grid-aligned 4D anchor features. Each anchor is processed by an MLP to spawn a set of neural 4D Gaussians, which represent a local spatiotemporal region. We design these neural 4D Gaussians to capture temporal changes with minimal parameters, making them well-suited for the MLP-based spawning. Moreover, we introduce a dynamic-aware anchor growing strategy to effectively assign additional anchors to under-reconstructed dynamic regions. Our method adjusts the accumulated gradients with Gaussians' temporal coverage, significantly improving reconstruction quality in dynamic regions. Experimental results highlight that our method achieves state-of-the-art visual quality in dynamic regions, outperforming all baselines by a large margin with practical storage costs.

Zitieren

APA

Cho, W. O., Cho, I., Kim, S., Bae, J., Uh, Y., & Kim, S. J. (2026). 4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3363-3371. https://doi.org/10.1609/aaai.v40i5.37332

Vancouver

Cho WO, Cho I, Kim S, Bae J, Uh Y, Kim SJ. 4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3363-3371. doi:10.1609/aaai.v40i5.37332

BibTeX
@article{Cho2026,
  author = {Cho, Woong Oh and Cho, In and Kim, Seoha and Bae, Jeongmin and Uh, Youngjung and Kim, Seon Joo},
  title = {4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3363--3371},
  doi = {10.1609/aaai.v40i5.37332}
}
Kostenlos starten →