Jiequan Zhang

Papers

Total Citations

H-Index

About

Jiequan Zhang is a researcher at the forefront of 3D computer vision and geometric deep learning, with a primary focus on shape assembly and physical reasoning. His work addresses a critical gap in autonomous robotic assembly and CAD modeling: while prior methods emphasized purely geometric reasoning, Zhang’s research pioneers the integration of physical assembly processes—specifically the matching and fitting of joints—into shape composition. His most cited paper, “Category-Level Multi-Part Multi-Joint 3D Shape Assembly” (2024, 13 citations), introduces a novel framework that reasons about both part geometries and their mechanical connections, enabling more realistic and functional assembly of complex 3D shapes. This work has significant implications for robotics, enabling systems to not only recognize object parts but also understand how they physically connect and move. Zhang’s contributions bridge the gap between virtual modeling and real-world assembly, advancing the field toward autonomous construction and repair. With a growing citation impact, his research is increasingly recognized for its practical relevance, offering a foundation for future work in embodied AI, manufacturing, and interactive 3D design.