Puming Wang
Papers
1
Total Citations
1
H-Index
1
About
Puming Wang is a researcher whose work pushes the boundaries of three-dimensional point cloud analysis, with a particular focus on developing novel geometric representations for machine learning. His most-cited paper, "Polyhedral representations with high-frequency for three-dimensional point cloud classification" (2025), introduces an innovative approach that leverages polyhedral structures to capture high-frequency geometric details in 3D data, significantly enhancing classification accuracy. This work addresses a critical challenge in 3D computer vision: the loss of fine-grained shape information in traditional point cloud processing methods. Wang's contributions are especially valuable for applications in autonomous navigation, robotics, and augmented reality, where precise spatial understanding is essential. While his citation count is still growing—reflecting the recent publication of his key work—his research has already attracted attention for its theoretical novelty and practical potential. By bridging geometric deep learning with classical polyhedral theory, Wang is helping to define a new direction for 3D data representation, promising more robust and efficient systems for interpreting complex real-world environments.
Research Focus
Key Achievements
Top Papers
- 1