DentalGS: Pose-Free 3D Gaussian Splatting from Five Intraoral Images for Novel View Synthesis
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3461-3469
DOI: 10.1609/aaai.v40i5.37343 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Honghao Dai und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Orthodontic treatment needs regular tooth alignment checks, but current methods depend on clinic visits, limiting remote care. With the emergence of 3D Gaussian Splatting (3DGS), realistic novel views can be synthesized, making it possible for clinicians to remotely monitor orthodontic conditions. However, using only five intraoral images with unknown camera poses and dynamic lighting presents major challenges in dental applications. To address these challenges, we propose DentalGS, an enhanced 3DGS framework capable of synthesizing novel intraoral views from five post-orthodontic intraoral images and pre-orthodontic intraoral scan (IOS) data as prior, without camera poses. Our method initializes a Gaussian point cloud labeled with ISO-FDI tooth classes based on the patient’s pre-orthodontic IOS data, then estimates camera poses through iterative optimization. We introduce a Progressive Pair Generation Strategy as a data augmentation method that generates damage–repair image pairs to train a RepairNet, aiming to restore degraded geometry and appearance caused by the limited number of intraoral images. Additionally, we introduce a Lighting-Aware 3DGS inspired by physical reflectance properties to mitigate the effects of dynamic lighting conditions. Experimental results show that our method produces high-quality novel views while preserving geometric structure even under extreme viewpoints, offering an efficient and reliable solution for 3D tooth visualization in remote orthodontic monitoring.
Zitieren
APA
Dai, H., Zhou, Y., Wei, G., Li, Z., & Wang, W. (2026). DentalGS: Pose-Free 3D Gaussian Splatting from Five Intraoral Images for Novel View Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3461-3469. https://doi.org/10.1609/aaai.v40i5.37343
Vancouver
Dai H, Zhou Y, Wei G, Li Z, Wang W. DentalGS: Pose-Free 3D Gaussian Splatting from Five Intraoral Images for Novel View Synthesis. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3461-3469. doi:10.1609/aaai.v40i5.37343
BibTeX
@article{Dai2026,
author = {Dai, Honghao and Zhou, Yuanfeng and Wei, Guangshun and Li, Zhihao and Wang, Wenping},
title = {DentalGS: Pose-Free 3D Gaussian Splatting from Five Intraoral Images for Novel View Synthesis},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {5},
pages = {3461--3469},
doi = {10.1609/aaai.v40i5.37343}
}
EUVIMED