Jianwang Gan

China University of Mining and Technology

Papers

Total Citations

H-Index

About

Jianwang Gan is a researcher advancing the frontiers of 3D perception and autonomous systems, with a primary focus on scene flow estimation from LiDAR point clouds. His work addresses the critical challenge of predicting point-wise 3D displacement from sequential sensor data—a fundamental capability for robotics and autonomous driving. Gan’s most notable contribution is the development of the "Multiscale Neighborhood Cluster Scene Flow Prior," a novel framework that leverages multiscale spatial priors to dramatically improve the accuracy of scene flow estimation from sparse point clouds. This approach tackles the inherent difficulty of modeling motion in unstructured 3D environments, offering a robust solution that outperforms prior-based models. While his 2024 paper has begun to accumulate citations, Gan’s research is positioned to have significant impact in enabling safer, more reliable autonomous navigation and robotic interaction. His work bridges the gap between theoretical geometry and practical deployment, making him a rising voice in the computer vision and robotics communities.