Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian
ACM Transactions on Graphics · 05.12.2023 · 42 (6) · 1-14
DOI: 10.1145/3618311 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 05.12.2023. Verfasst von Zixiong Wang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 67 Literaturangaben. Gefördert von: Natural Science Foundation of Shandong Province, SpecialFunds for Taishan Scholars Project, National Key R&D Program of China.
Abstract (Originalsprache)
Neural implicit representation is a promising approach for reconstructing surfaces from point clouds. Existing methods combine various regularization terms, such as the Eikonal and Laplacian energy terms, to enforce the learned neural function to possess the properties of a Signed Distance Function (SDF). However, inferring the actual topology and geometry of the underlying surface from poor-quality unoriented point clouds remains challenging. In accordance with Differential Geometry, the Hessian of the SDF is singular for points within the differential thin-shell space surrounding the surface. Our approach enforces the Hessian of the neural implicit function to have a zero determinant for points near the surface. This technique aligns the gradients for a near-surface point and its on-surface projection point, producing a rough but faithful shape within just a few iterations. By annealing the weight of the singular-Hessian term, our approach ultimately produces a high-fidelity reconstruction result. Extensive experimental results demonstrate that our approach effectively suppresses ghost geometry and recovers details from unoriented point clouds with better expressiveness than existing fitting-based methods.
Förderung
- Natural Science Foundation of Shandong Province
- SpecialFunds for Taishan Scholars Project
- National Key R&D Program of China
- National Natural Science Foundation of China
Zitieren
APA
Wang, Z., Zhang, Y., Xu, R., Zhang, F., Wang, P., Chen, S., Xin, S., Wang, W., & Tu, C. (2023). Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian. ACM Transactions on Graphics, 42(6), 1-14. https://doi.org/10.1145/3618311
Vancouver
Wang Z, Zhang Y, Xu R, Zhang F, Wang P, Chen S, et al. Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian. ACM Transactions on Graphics. 2023;42(6):1-14. doi:10.1145/3618311
BibTeX
@article{Wang2023,
author = {Wang, Zixiong and Zhang, Yunxiao and Xu, Rui and Zhang, Fan and Wang, Peng-Shuai and Chen, Shuangmin and Xin, Shiqing and Wang, Wenping and Tu, Changhe},
title = {Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian},
journal = {ACM Transactions on Graphics},
year = {2023},
volume = {42},
number = {6},
pages = {1--14},
doi = {10.1145/3618311}
}
EUVIMED