Lu Zou

University of Science and Technology of China

Papers

Total Citations

H-Index

About

Lu Zou is a researcher advancing the field of 3D computer vision, with a primary focus on 6D object pose estimation—a critical capability for robotic manipulation and augmented reality. Her work bridges the gap between visual and geometric understanding, particularly through the integration of cross-modal learning. In her highly cited 2021 paper "CMA: Cross-modal attention for 6D object pose estimation" (22 citations), she introduced a novel attention mechanism that fuses RGB and depth information, significantly improving pose accuracy for known objects. Building on this, her 2023 work "Learning geometric consistency and discrepancy for category-level 6D object pose estimation from point clouds" (22 citations) tackles the more challenging problem of estimating poses for unseen object instances. By leveraging point cloud geometry and enforcing consistency constraints, she addresses a fundamental limitation in prior RGB-focused approaches. Her contributions are particularly impactful for robotics, where reliable pose estimation under varying conditions is essential. With over 40 citations across her key papers, Zou is establishing herself as a rising voice in geometric deep learning, pushing the boundaries of how machines perceive and interact with 3D environments.