Ariel H. Curiale

Papers

Total Citations

H-Index

About

Ariel H. Curiale is a leading researcher in computer vision and geometric deep learning, with a primary focus on point cloud registration and shape matching. Their most influential work, "Accurate Point Cloud Registration with Robust Optimal Transport" (2021, 26 citations), introduces a groundbreaking approach that leverages robust optimal transport (OT) solvers to significantly enhance both optimization-based and deep learning methods for aligning 3D point clouds. By demonstrating that modern OT techniques can boost registration accuracy at a manageable computational cost, Curiale has provided a practical and theoretically sound framework for tackling one of the most fundamental challenges in 3D vision. This contribution bridges the gap between classical optimal transport theory and modern machine learning, offering a versatile tool for applications ranging from autonomous navigation to medical imaging. Curiale’s research is characterized by its rigorous mathematical foundation and its direct impact on real-world systems, making their work essential reading for students and researchers seeking to advance the state of the art in 3D data processing and geometric understanding.