Xuzhan Chen

About

Xuzhan Chen is a leading researcher in 3D computer vision and robotics perception, with a focus on enabling machines to understand and interact with three-dimensional environments. His work centers on object detection and recognition from point cloud data, addressing critical challenges in autonomous systems, industrial automation, and robotics. Chen’s most impactful contribution is a novel method for detecting 6D poses of target objects in cluttered scenes, which learns to align point cloud patches with CAD models—a technique that has garnered 12 citations and is foundational for applications in manufacturing and unmanned vehicles. He also advanced 3D object classification through a point convolution network (9 citations), balancing high-resolution representation with computational efficiency for real-world robot operation. Additionally, Chen has explored end-to-end approaches for 3D model retrieval by projecting point clouds onto discriminating 2D views, and robust point-cloud alignment using unsupervised deep learning. His work bridges the gap between raw sensor data and actionable spatial understanding, making him a key figure in the development of intelligent, perception-driven systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Detecting 6D Poses of Target Objects From Cluttered Scenes by Learning to Align the Point Cloud Patches With the CAD Models

   12 citations · 2020
2. 2
   3D object classification with point convolution network

   9 citations · 2017
3. 3
   End-to-end 3D object model retrieval by projecting the point cloud onto a unique discriminating 2D view

   5 citations · 2020
4. 4
   End to End Robust Point-Cloud Alignment Using Unsupervised Deep Learning

   2 citations · 2020

Key Collaborators

Contact & Links