EUVIMEDEUVIMED entdecken
Crossref

GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction

Zesong Yang, Ru Zhang, Jiale Shi, Zixiang Ai, Boming Zhao, Hujun Bao, Luwei Yang, Zhaopeng Cui

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (9) · 9363-9372

DOI: 10.1609/aaai.v39i9.33014 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Zesong Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural surface representation has demonstrated remarkable success in the areas of novel view synthesis and 3D reconstruction. However, assessing the geometric quality of 3D reconstructions in the absence of ground truth mesh remains a significant challenge, due to its rendering-based optimization process and entangled learning of appearance and geometry with photometric losses. In this paper, we present a novel framework, i.e, GURecon, which establishes a geometric uncertainty field for the neural surface based on geometric consistency. Different from existing methods that rely on rendering-based measurement, GURecon models a continuous 3D uncertainty field for the reconstructed surface, and is learned by an online distillation approach without introducing real geometric information for supervision. Moreover, in order to mitigate the interference of illumination on geometric consistency, a decoupled field is learned and exploited to finetune the uncertainty field. Experiments on various datasets demonstrate the superiority of GURecon in modeling 3D geometric uncertainty, as well as its plug-and-play extension to various neural surface representations and improvement on downstream tasks such as incremental reconstruction.

Zitieren

APA

Yang, Z., Zhang, R., Shi, J., Ai, Z., Zhao, B., Bao, H., Yang, L., & Cui, Z. (2025). GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 39(9), 9363-9372. https://doi.org/10.1609/aaai.v39i9.33014

Vancouver

Yang Z, Zhang R, Shi J, Ai Z, Zhao B, Bao H, et al. GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(9):9363-9372. doi:10.1609/aaai.v39i9.33014

BibTeX
@article{Yang2025,
  author = {Yang, Zesong and Zhang, Ru and Shi, Jiale and Ai, Zixiang and Zhao, Boming and Bao, Hujun and Yang, Luwei and Cui, Zhaopeng},
  title = {GURecon: Learning Detailed 3D Geometric Uncertainties for Neural Surface Reconstruction},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {9},
  pages = {9363--9372},
  doi = {10.1609/aaai.v39i9.33014}
}
Kostenlos starten →