Zongdai Liu
Papers
1
Total Citations
12
H-Index
1
About
Zongdai Liu is a researcher advancing the intersection of 3D computer vision and robotic interaction, with a focus on fine-grained object understanding. His most-cited work, "3D Part Guided Image Editing for Fine-Grained Object Understanding" (2020, 12 citations), introduces a novel framework that leverages 3D movable parts to enhance visual models for robotic perception. This approach is critical for autonomous systems, such as self-driving vehicles, which must interpret dynamic object behaviors like door openings or taillight signals to navigate safely. By bridging 3D geometry and image editing, Liu’s research enables robots to holistically understand object functionality, moving beyond static recognition to actionable part dynamics. His contributions are foundational for embodied AI, where precise part-level comprehension is key to real-world interaction. With a growing citation impact, Liu’s work is shaping how machines perceive and interact with complex, dynamic environments, positioning him as a rising voice in computer vision and robotics.
Research Focus
Key Achievements
Top Papers
- 13D Part Guided Image Editing for Fine-Grained Object Understanding12 citations · 2020