Chunyu Tan
Papers
1
Total Citations
7
H-Index
1
About
Chunyu Tan is a rising researcher at the forefront of energy-efficient 3D computer vision, with a primary focus on spiking neural networks (SNNs) and point cloud processing. Their most-cited work, "Point-to-Spike Residual Learning for Energy-Efficient 3D Point Cloud Classification" (2024, 7 citations), pioneers the application of SNNs—neural architectures inspired by biological learning that consume ultra-low power—to the challenging domain of 3D point cloud analysis. This contribution is significant because it bridges the gap between SNNs' proven success in image analysis and robot control and the underexplored area of 3D spatial data, offering a path toward sustainable, real-time perception for autonomous systems. By introducing a residual learning framework that converts point cloud inputs into spike trains, Tan demonstrates how to maintain classification accuracy while dramatically reducing energy consumption compared to traditional artificial neural networks. This work positions Tan as an innovator in green AI, with potential impacts on robotics, autonomous driving, and edge computing. Their research represents a critical step toward making advanced 3D perception both practical and environmentally sustainable.
Research Focus
Key Achievements
Top Papers
- 1