Ekin Celikkan

Papers

Total Citations

H-Index

About

Ekin Celikkan is a researcher at the forefront of 3D computer vision and interactive machine learning, with a primary focus on point cloud segmentation. Their most cited work, "Interactive Object Segmentation in 3D Point Clouds" (2023, 24 citations), pioneers a novel paradigm that enables users to iteratively collaborate with deep learning models to segment objects directly in 3D space. This approach addresses a critical limitation of fully-supervised methods, which require extensive labeled datasets, by introducing human-in-the-loop interaction that reduces annotation burden while improving segmentation accuracy. Celikkan’s contributions are particularly impactful for applications in autonomous driving, robotics, and augmented reality, where efficient 3D scene understanding is essential. By bridging the gap between manual annotation and automated segmentation, their work empowers researchers and practitioners to achieve high-quality results with minimal data. With a growing citation record and a clear trajectory toward more interactive, user-centric AI systems, Celikkan is establishing themselves as an innovator in making 3D deep learning more accessible and practical for real-world deployment.