Weijie Lv

Papers

Total Citations

H-Index

About

Weijie Lv is a leading researcher in computer vision and robotics, specializing in 6-Degrees-of-Freedom (6DoF) pose estimation for complex, real-world environments. His core contributions address the critical challenge of accurately detecting and positioning objects in cluttered, stacked scenarios—a problem central to industrial automation and robotic manipulation. Lv’s work, particularly through his highly cited paper “PPR-Net++: Accurate 6-D Pose Estimation in Stacked Scenarios” (2021, 39 citations), pioneers novel supervised learning frameworks that overcome the domain shift between synthetic training data and real-world testing conditions. He further advanced the field with “ParametricNet++: A 6DoF Pose Estimation Network with Sparse Keypoint Recovery for Parametric Shapes in Stacked Scenarios” (2024), which tackles the inherent diversity and uncertainty of industrial parametric parts. By integrating pointwise regression with sparse keypoint recovery, Lv’s methods achieve robust, precise pose estimation where traditional approaches fail. His research directly impacts manufacturing, logistics, and robotics, enabling machines to perceive and interact with unstructured environments. With a growing citation record and a focus on bridging simulation and reality, Weijie Lv is a rising authority in practical, high-accuracy pose estimation for stacked and parametric objects.