EUVIMEDEUVIMED entdecken
Crossref

Non-Rigid Point Cloud Registration via Anisotropic Hybrid Field Harmonization

Jinyang Wang, Xuequan Lu, Mohammed Bennamoun, Bin Sheng

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-09 · 47 (9) · 7898-7915

DOI: 10.1109/tpami.2025.3572584 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-09. Verfasst von Jinyang Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 91 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current point cloud registration algorithms struggle to effectively handle both deformations and occlusions simultaneously. Our manifold analysis reveals this limitation arises from the inaccurate modeling of the shape's underlying manifold and the lack of an effective optimization strategy for fragmented manifold structures. In this paper, we present AniSym-Net, a novel non-rigid registration framework designed to address near-isometric deformation registration in the presence of occlusions. To encode object's coarse topological properties and local geometric information, AniSym-Net introduces a novel anisotropic hybrid shape-motion deformation field. The effectiveness of the anisotropic hybrid shape-motion fields relies on both the holonomic constraints from the symplectic structure modeling in AniSym-Net and the motion-conditional cross-attention during fusion, which calibrates geometric features using velocity-boundary constrained point motion patterns. The harmonization of correspondences derived from anisotropic hybrid fields and those from motion-shape fields significantly mitigates registration errors and occlusions. This is achieved through the optimization of loop closures of cotangent bundles within the symplectic manifold framework. We conduct comprehensive evaluation across five popular benchmarks, namely CAPE, DT4D, SAPIEN, FAUST, and DeepDeform, to demonstrate our AniSym-Net's superior performance compared to the state-of-the-art methods. Code will be publicly available.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Wang, J., Lu, X., Bennamoun, M., & Sheng, B. (2025). Non-Rigid Point Cloud Registration via Anisotropic Hybrid Field Harmonization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(9), 7898-7915. https://doi.org/10.1109/tpami.2025.3572584

Vancouver

Wang J, Lu X, Bennamoun M, Sheng B. Non-Rigid Point Cloud Registration via Anisotropic Hybrid Field Harmonization. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(9):7898-7915. doi:10.1109/tpami.2025.3572584

BibTeX
@article{Wang2025,
  author = {Wang, Jinyang and Lu, Xuequan and Bennamoun, Mohammed and Sheng, Bin},
  title = {Non-Rigid Point Cloud Registration via Anisotropic Hybrid Field Harmonization},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {9},
  pages = {7898--7915},
  doi = {10.1109/tpami.2025.3572584}
}
Kostenlos starten →