Papers
4
Total Citations
103
H-Index
4
About
Zichang Liu is a researcher specializing in computer vision and robotics, with a primary focus on category-level 6D object pose and size estimation. His most significant contribution is the development of SAR-Net (Shape Alignment and Recovery Network), a novel approach that estimates the 6D pose and size of objects from a single scene image or depth observation, without requiring external real-world pose-annotated training data. This work, which has garnered 86 citations, leverages rich geometric information from point clouds to overcome the limitations of traditional RGB-based methods. Liu’s research addresses a critical challenge in robotic manipulation and augmented reality: enabling machines to understand and interact with unseen objects in their environment. He has also explored team formation optimization for RoboCup 3D soccer robots, applying Delaunay triangulation to enhance collaborative strategies. His work on DONet further extends category-level pose estimation using only depth data, demonstrating versatility across sensing modalities. Liu’s contributions are foundational for advancing autonomous systems that require robust, generalizable object understanding.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4