Papers
1
Total Citations
27
H-Index
1
About
Yaoran Huang is a leading researcher in 3D geometric processing and computer graphics, with a primary focus on feature extraction from unstructured point cloud data. His most cited work, "Multiscale Feature Line Extraction From Raw Point Clouds Based on Local Surface Variation and Anisotropic Contraction" (2021, 27 citations), introduces a pioneering method that directly extracts salient feature lines from raw, unstructured 3D scans without requiring surface reconstruction or normal estimation. By leveraging local surface variation and anisotropic contraction, Huang’s approach preserves multiscale geometric details—from sharp edges to subtle creases—enabling robust shape analysis for applications in reverse engineering, cultural heritage preservation, and autonomous navigation. This work addresses a critical bottleneck in 3D data processing: the lack of higher-level structural cues in low-level point clouds. Huang’s contributions have been widely recognized for advancing the automation of geometric feature detection, with his methods cited in subsequent research on point cloud simplification, segmentation, and registration. His achievements underscore a commitment to bridging raw sensor data and meaningful geometric understanding, making him a notable figure in the field of computational geometry.
Research Focus
Key Achievements
Top Papers
- 1