Irem Kaftan
Papers
1
Total Citations
19
H-Index
1
About
Irem Kaftan is a rising researcher at the intersection of computer vision and graphics, with a primary focus on 3D scene understanding and human-centric perception. Her most impactful work tackles the challenging problem of segmenting humans in 3D point clouds, a critical capability for applications in human-centered robotics, augmented reality, and virtual reality. In her highly cited 2023 paper, Kaftan introduced a novel framework for joint 3D human semantic segmentation, instance segmentation, and multi-human body-part segmentation—a task few had attempted due to the scarcity of labeled real-world data. By leveraging synthetic data to train robust models, she demonstrated that high-quality 3D human segmentation is achievable without expensive manual annotation, achieving 19 citations in just over a year. This work not only advances the state of the art in 3D perception but also provides a scalable solution for real-world deployment. Kaftan’s contributions are paving the way for more immersive and interactive digital environments, marking her as a promising innovator in the field.
Research Focus
Key Achievements
Top Papers
- 13D Segmentation of Humans in Point Clouds with Synthetic Data19 citations · 2023