Bijective Shape Correspondence through Nonlinear Spectral Embedding Alignment
Computer Graphics Forum · 14.11.2026
DOI: 10.1111/cgf.70620 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 14.11.2026. Verfasst von Jianhui Liu und 2 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Beijing Municipality.
Abstract (Originalsprache)
Bijective correspondence is essential for texture and signal transfer, serving as a core benchmark for shape matching quality. Although the recently proposed Neural Adjoint Map (NAM) advances 3D shape correspondence by generalizing linear spectral alignment to nonlinear, network‐parameterized functions, it is inherently unidirectional, failing to guarantee map bijectivity; on the other hand, existing spectral embedding alignment methods that promote bijectivity rely on the reciprocal property of low‐dimensional functional maps, which we point out potentially introduces an isometric mapping prior and degrades accuracy under non‐isometric scenarios. To address these issues, we propose the Bijective Neural Adjoint Map (BNAM), a novel framework that bridges bidirectional NAMs under a soft invertibility constraint to encourage mutual bijectivity. Additionally, we introduce an iterative upsampling pipeline to efficiently estimate BNAM. Our method promotes map bijectivity while preserving mapping accuracy across challenging scenarios, including near‐/non‐isometric meshes and unstructured point clouds.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Beijing Municipality
Zitieren
APA
Liu, J., Wu, Z., & Wang, X. (2026). Bijective Shape Correspondence through Nonlinear Spectral Embedding Alignment. Computer Graphics Forum. https://doi.org/10.1111/cgf.70620
Vancouver
Liu J, Wu Z, Wang X. Bijective Shape Correspondence through Nonlinear Spectral Embedding Alignment. Computer Graphics Forum. 2026. doi:10.1111/cgf.70620
BibTeX
@article{Liu2026,
author = {Liu, Jianhui and Wu, Zhongke and Wang, Xingce},
title = {Bijective Shape Correspondence through Nonlinear Spectral Embedding Alignment},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70620}
}
EUVIMED