Cien Fan

Papers

Total Citations

H-Index

About

Cien Fan is a researcher whose work lies at the intersection of 3D perception and computer vision, with a focus on advancing object detection and recognition systems. Fan’s most impactful contribution is the development of **PSANet (Pyramid Splitting and Aggregation Network)**, a novel architecture for 3D object detection in LiDAR point clouds. This work, which has garnered 22 citations, directly addresses the performance bottlenecks in one-stage 3D detectors by improving the utilization of bird’s-eye-view features, a critical step for applications in autonomous driving and robotics. Beyond 3D perception, Fan has explored face age classification using deep hybrid models and improved real-time object proposal generation through local binary patterns, demonstrating a broad interest in efficient, real-time visual understanding. While still early in their career, Fan’s contributions to 3D detection—a rapidly growing field—signal a focus on making autonomous systems faster and more accurate. Their work is particularly relevant for students and researchers working on point cloud processing, autonomous navigation, and efficient object recognition pipelines.