Zhuo Su
Papers
1
Total Citations
12
H-Index
1
About
Zhuo Su is a rising researcher in 3D computer vision and geometric deep learning, with a focus on making point cloud processing both efficient and robust for real-world deployment. Their most-cited work, "SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation" (2022, 12 citations), tackles a critical challenge at the intersection of equivariant neural networks and model compression. Su introduces a general framework that marries SO(3) equivariance—ensuring consistent predictions under 3D rotations—with network binarization, drastically reducing model size and computational cost. This innovation is particularly vital for edge applications such as autonomous driving and robotics, where real-time, reliable 3D perception is essential. By demonstrating that equivariant properties can be preserved even in highly compressed binary networks, Su’s work opens new pathways for deploying sophisticated 3D models on resource-constrained devices. Their research addresses a growing need for efficiency without sacrificing geometric fidelity, marking a significant step toward practical, on-device 3D understanding. As a young scholar, Su’s contributions are already shaping how the field balances theoretical rigor with real-world constraints.
Research Focus
Key Achievements
Top Papers
- 1