Fengda Hao

Papers

Total Citations

H-Index

About

Fengda Hao is a researcher specializing in 3D computer vision and geometric deep learning, with a particular focus on point cloud processing. His most notable contribution is the development of the Cascaded Geometric Feature Modulation Network, a novel architecture designed to enhance the representation and manipulation of irregular 3D point cloud data. This work, published in 2022, introduces a cascaded modulation mechanism that effectively captures multi-scale geometric features, improving performance in tasks such as classification, segmentation, and detection. While his citation count is still building—with 4 citations for his flagship paper—Hao’s research addresses a critical challenge in the field: efficiently processing unstructured point clouds without sacrificing geometric fidelity. His approach stands out for its ability to integrate local and global geometric cues through a hierarchical modulation process, offering a more robust alternative to traditional methods. As the demand for precise 3D understanding grows in autonomous driving, robotics, and AR/VR, Hao’s work lays a strong foundation for future advancements. His contributions are particularly valuable for students and researchers exploring how deep learning can bridge the gap between raw sensor data and high-level semantic interpretation in 3D environments.