Catherine Capellen

Papers

Total Citations

H-Index

About

Catherine Capellen is a researcher in computer vision and robotics, with a primary focus on 6D object pose estimation—a critical task for enabling machines to perceive and interact with their environments. Her work centers on developing deep learning architectures that predict and refine dense, accurate object poses from visual data, bridging the gap between simulation and real-world application. Capellen’s most cited paper, “ConvPoseCNN2: Prediction and Refinement of Dense 6D Object Pose” (2022), introduces a convolutional neural network framework that iteratively improves pose estimates, achieving high precision even under challenging conditions like occlusion or cluttered scenes. While her citation count is still growing, this work represents a meaningful contribution to the field, offering a robust method for robotic manipulation and augmented reality. Capellen’s research is characterized by a commitment to dense, per-pixel prediction and refinement strategies, which enhance the reliability of pose estimation systems. As her publications gain traction, she is poised to influence the next generation of vision-based robotics, making her a researcher to watch for those interested in the intersection of deep learning and spatial understanding.