Duygu Ceylan

Papers

Total Citations

216

H-Index

About

Duygu Ceylan is a leading researcher in computer vision and computer graphics, with a focus on 3D shape understanding, generation, and representation. Her major contributions lie in developing structured and abstract models of the 3D world, enabling machines to perceive and create complex shapes from limited data. Her most cited work, "3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks" (2017), has garnered 194 citations, demonstrating its significant impact. This research introduces a novel approach inspired by human perception, decomposing 3D shapes into collections of simple primitives using recurrent neural networks. The work has profound implications for robotics, digital content creation, and visualization, offering a more intuitive and efficient way to represent 3D geometry. Ceylan’s achievements highlight her ability to bridge the gap between human-like understanding and machine learning, making her a pivotal figure in advancing 3D modeling and its real-world applications. Her research continues to inspire new directions in structured shape generation and abstraction.