Songfang Han
Papers
1
Total Citations
20
H-Index
1
About
Songfang Han is a leading researcher in computer vision and embodied AI, with a focus on bridging the sim-to-real gap for autonomous systems. Her most impactful work centers on physics-grounded sensor simulation, particularly for active stereo depth sensors—a critical component in robotics and autonomous driving. In her highly cited 2023 paper, Han introduced a fully physics-grounded simulation pipeline that models material acquisition and ray-tracing to replicate real-world sensor behavior. This breakthrough enables more realistic training environments for perception models, significantly reducing the domain gap between simulation and deployment. With over 20 citations in just two years, her work is rapidly shaping how researchers approach sensor simulation for embodied agents. Han’s contributions are essential for advancing robust vision systems in robotics, where accurate depth perception is paramount. Her research not only improves the fidelity of synthetic data but also paves the way for safer, more reliable autonomous systems. For students and researchers exploring sensor simulation or sim-to-real transfer, Han’s work offers a rigorous, principled foundation that is already influencing both academic and industry practices.
Research Focus
Key Achievements
Top Papers
- 1