SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting
ACM Transactions on Graphics · 30.04.2025 · 44 (2) · 1-11
DOI: 10.1145/3727143 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 12.04.2025. Verfasst von Sara Sabour und 8 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Three-dimensional Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering efficient training and rendering speeds, making it suitable for real-time applications. However, current methods require highly controlled environments–no moving people or wind-blown elements, and consistent lighting–to meet the interview consistency assumption of 3DGS. This makes reconstruction of real-world captures problematic. We present SpotLessSplats, an approach that leverages pre-trained and general-purpose features coupled with robust optimization to effectively ignore transient distractors. Our method achieves state-of-the-art reconstruction quality both visually and quantitatively, on casual captures.
Zitieren
APA
Sabour, S., Goli, L., Kopanas, G., Matthews, M., Lagun, D., Guibas, L., Jacobson, A., Fleet, D., & Tagliasacchi, A. (2025). SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting. ACM Transactions on Graphics, 44(2), 1-11. https://doi.org/10.1145/3727143
Vancouver
Sabour S, Goli L, Kopanas G, Matthews M, Lagun D, Guibas L, et al. SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting. ACM Transactions on Graphics. 2025;44(2):1-11. doi:10.1145/3727143
BibTeX
@article{Sabour2025,
author = {Sabour, Sara and Goli, Lily and Kopanas, George and Matthews, Mark and Lagun, Dmitry and Guibas, Leonidas and Jacobson, Alec and Fleet, David and Tagliasacchi, Andrea},
title = {SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {2},
pages = {1--11},
doi = {10.1145/3727143}
}
EUVIMED