Max Robotics — Global Service Robot Directory + US Certification

About

Zhenyu He is a computer vision researcher specializing in human pose estimation and object pose estimation, with a particular focus on advancing deep learning methods for understanding spatial relationships in complex visual scenes. His highly cited 2021 review, "Deep 3D Human Pose Estimation: A Review," has garnered over 383 citations, establishing him as an authoritative voice in the field and providing the research community with a comprehensive synthesis of techniques for recovering articulated 3D joint locations from images and video — a foundational challenge with far-reaching applications in human-computer interaction, motion analysis, and robotics. More recently, He has pioneered zero-shot object 6D pose estimation, introducing the ZeroPose framework, which leverages CAD model prompting to estimate the position and orientation of novel, previously unseen objects in cluttered scenes — a significant departure from object-specific methods that struggle to generalize. His continued work, including ZeroBP for bin-picking environments featuring texture-less and randomly stacked workpieces, demonstrates a clear trajectory toward practical, generalizable robotic perception solutions. Together, his contributions reflect a research vision that bridges fundamental computer vision theory with real-world industrial and robotic applications.