Fangdi Jiang

Changchun University of Science and Technology

Papers

Total Citations

H-Index

About

Fangdi Jiang is a rising researcher at the forefront of autonomous driving perception and 3D scene understanding, with a focus on LiDAR-based systems. Their work addresses two critical challenges in robotics: robust 3D object detection and simultaneous localization and mapping (SLAM). In their highly cited 2024 paper, "STFNET: Sparse Temporal Fusion for 3D Object Detection in LiDAR Point Cloud" (6 citations), Jiang introduced a novel framework that leverages temporal information across sparse point cloud sequences to overcome noise, occlusions, and sparsity—key limitations of single-frame detectors. This work has quickly gained traction for its practical impact on real-time autonomous navigation. Building on this, Jiang's 2025 paper, "NDF-SLAM: LiDAR SLAM based on neural distance field for registration and loop closure detection" (3 citations), pioneers the integration of neural implicit representations into LiDAR SLAM, enabling more accurate registration and loop closure. By fusing neural distance fields with traditional geometric pipelines, Jiang offers a path toward more resilient mapping in complex environments. Though early in their career, Jiang's contributions are already shaping next-generation perception systems for autonomous vehicles and robotics, demonstrating a clear trajectory toward high-impact, deployable solutions.