Upright-Net+: Enhanced learning of upright orientation for 3D point clouds
Publication Type
Journal Article
Publication Date
12-2025
Abstract
Automatic 3D shape analysis is heavily influenced by the pose of input 3D models, as the continuous nature of pose space introduces complexities that usually exceed the encoding capacities of standard deep learning frameworks. To tackle this challenge, we present Upright-Net+, an enhancement of our previous model, Upright-Net, specifically developed for estimating upright orientation in 3D point clouds. Our approach is grounded in the design principle that ”form ever follows function,” treating the natural base of an object as a functional structure that stabilizes it in its typical pose, influenced by physical laws and geometric properties. We reformulate the continuous orientation problem into a discrete classification task, focusing on learning the points that constitute the natural base of a 3D model. The upright orientation is determined by aligning the normal orientation of this base towards the mass center. To mitigate over-smoothing in the global feature embeddings from stacked graph convolutional layers, we introduce a Global Positional Encoding Module using Relative Distance Histogram Statistics Embedding (GPE-RDHS), which reduces structural ambiguity and enhances orientation estimation. We also enhanced a weighted residual loss term to penalize false positive predictions, enhancing overall model performance. Our method demonstrates exceptional performance in upright orientation estimation and reveals that the learned orientation-aware features significantly benefit downstream tasks, particularly in classification.
Keywords
Upright orientation, point cloud, feature extraction, transferability, representation learning, orientation-aware feature embedding, geometric structure descriptors, representation learning, three-dimensional displays, point cloud analysis, point cloud classification
Discipline
Graphics and Human Computer Interfaces | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
IEEE Transactions on Visualization and Computer Graphics
Volume
31
Issue
12
First Page
10545
Last Page
10560
ISSN
1077-2626
Identifier
10.1109/TVCG.2025.3605201
Publisher
Institute of Electrical and Electronics Engineers
Citation
PANG, Xufang; LI, Feng; ZHUANG, Hongjie; DING, Ning; ZHONG, Xiaopin; HE, Shengfeng; LIU, Wenxi; and JIANG, Bo.
Upright-Net+: Enhanced learning of upright orientation for 3D point clouds. (2025). IEEE Transactions on Visualization and Computer Graphics. 31, (12), 10545-10560.
Available at: https://ink.library.smu.edu.sg/sis_research/10537
Copyright Owner and License
Authors
Additional URL
https://doi.org/10.1109/TVCG.2025.3605201