EUVIMEDEUVIMED entdecken
Crossref

Real-time Large-scale Deformation of Gaussian Splatting

Lin Gao, Jie Yang, Bo-Tao Zhang, Jia-Mu Sun, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai

ACM Transactions on Graphics · 19.12.2024 · 43 (6) · 1-17

DOI: 10.1145/3687756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.11.2024. Verfasst von Lin Gao und 6 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 104 Literaturangaben. Gefördert von: Innovation Funding of ICT, CAS, National Natural Science Foundation of China, Beijing Municipal Natural Science Foundation for Distinguished Young Scholars.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural implicit representations, including Neural Distance Fields and Neural Radiance Fields, have demonstrated significant capabilities for reconstructing surfaces with complicated geometry and topology, and generating novel views of a scene. Nevertheless, it is challenging for users to directly deform or manipulate these implicit representations with large deformations in a real-time fashion. Gaussian Splatting (GS) has recently become a promising method with explicit geometry for representing static scenes and facilitating high-quality and real-time synthesis of novel views. However, it cannot be easily deformed due to the use of discrete Gaussians and the lack of explicit topology. To address this, we develop a novel GS-based method (GaussianMesh) that enables interactive deformation. Our key idea is to design an innovative mesh-based GS representation, which is integrated into Gaussian learning and manipulation. 3D Gaussians are defined over an explicit mesh, and they are bound with each other: the rendering of 3D Gaussians guides the mesh face split for adaptive refinement, and the mesh face split directs the splitting of 3D Gaussians. Moreover, the explicit mesh constraints help regularize the Gaussian distribution, suppressing poor-quality Gaussians ( e.g. , misaligned Gaussians, long-narrow shaped Gaussians), thus enhancing visual quality and reducing artifacts during deformation. Based on this representation, we further introduce a large-scale Gaussian deformation technique to enable deformable GS, which alters the parameters of 3D Gaussians according to the manipulation of the associated mesh. Our method benefits from existing mesh deformation datasets for more realistic data-driven Gaussian deformation. Extensive experiments show that our approach achieves high-quality reconstruction and effective deformation, while maintaining the promising rendering results at a high frame rate (65 FPS on average on a single commodity GPU).

Förderung

  • Innovation Funding of ICT, CAS
  • National Natural Science Foundation of China
  • Beijing Municipal Natural Science Foundation for Distinguished Young Scholars
  • Beijing Municipal Science and Technology Commission

Zitieren

APA

Gao, L., Yang, J., Zhang, B., Sun, J., Yuan, Y., Fu, H., & Lai, Y. (2024). Real-time Large-scale Deformation of Gaussian Splatting. ACM Transactions on Graphics, 43(6), 1-17. https://doi.org/10.1145/3687756

Vancouver

Gao L, Yang J, Zhang B, Sun J, Yuan Y, Fu H, et al. Real-time Large-scale Deformation of Gaussian Splatting. ACM Transactions on Graphics. 2024;43(6):1-17. doi:10.1145/3687756

BibTeX
@article{Gao2024,
  author = {Gao, Lin and Yang, Jie and Zhang, Bo-Tao and Sun, Jia-Mu and Yuan, Yu-Jie and Fu, Hongbo and Lai, Yu-Kun},
  title = {Real-time Large-scale Deformation of Gaussian Splatting},
  journal = {ACM Transactions on Graphics},
  year = {2024},
  volume = {43},
  number = {6},
  pages = {1--17},
  doi = {10.1145/3687756}
}
Kostenlos starten →