Lianghao Han
Papers
1
Total Citations
2
H-Index
1
About
Lianghao Han is a rising researcher at the intersection of computer vision and neuromorphic computing, with a focus on energy-efficient perception systems. His primary research areas include depth estimation, event-based vision, and knowledge distillation for embedded AI. Han’s most notable contribution is the development of a novel spike transformer network that achieves accurate depth estimation from event cameras—bio-inspired sensors that capture asynchronous light changes as binary spikes. By leveraging cross-modality knowledge distillation, his work bridges the gap between conventional frame-based and event-based vision, enabling high performance with drastically reduced energy consumption. This approach is particularly impactful for autonomous navigation, robotics, and augmented reality, where low latency and power efficiency are critical. His 2025 paper on this topic has already garnered early citations, signaling growing recognition in the field. Han’s research addresses a key challenge in deploying deep learning on resource-constrained platforms, positioning him as an innovator in sustainable AI for real-world vision systems.
Research Focus
Key Achievements
Top Papers
- 1