Zhongyao Cheng

About

Zhongyao Cheng is a rising researcher in computer vision and 3D geometric deep learning, with a primary focus on point cloud analysis and few-shot learning. His most-cited work, "Cascade Graph Neural Networks for Few-Shot Learning on Point Clouds" (2023, 9 citations), addresses a critical bottleneck in 3D scene understanding: the heavy reliance on manual annotation for point cloud data. By introducing a cascade graph neural network architecture, Cheng enables effective learning from very limited labeled examples, significantly reducing the need for costly human supervision in applications like autonomous driving, robotics, and remote sensing. This contribution is particularly impactful as it bridges the gap between the flexibility of point cloud representations and the practical constraints of data annotation in real-world deployments. Cheng's research demonstrates a keen ability to tackle fundamental challenges in 3D perception, pushing the boundaries of how machines can learn from sparse, unstructured spatial data. His work is paving the way for more efficient and scalable 3D vision systems, making him a promising voice in the next generation of geometric deep learning researchers.

Research Focus

Key Achievements

Top Papers

1. 1
   Cascade Graph Neural Networks for Few-Shot Learning on Point Clouds

   9 citations · 2023

Key Collaborators

Contact & Links