Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning

Chenyu Hu; Xiaotong Li; Hao Zhu; Biao Hou

AAAI 2026technical0 citations

Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning

Chenyu Hu, Xiaotong Li, Hao Zhu, Biao Hou

Abstract

Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The core of this issue is the disruption of the point cloud

BibTeX

@inproceedings{aaai2026_hierarchicaldire,
  title = {Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning},
  author = {Chenyu Hu and Xiaotong Li and Hao Zhu and Biao Hou},
  booktitle = {AAAI 2026},
  year = {2026}
}