Apostolia Tsirikoglou
Papers
1
Total Citations
38
H-Index
1
About
Apostolia Tsirikoglou is a leading researcher at the intersection of computer graphics and computer vision, with a primary focus on synthetic data generation for deep learning. Her most impactful work, "Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications" (2017, 38 citations), introduces a groundbreaking systematic approach for creating highly realistic, annotated synthetic datasets. Tsirikoglou’s key contribution lies in her procedural world modeling technique, which enables unprecedented variability in generated scenes while maintaining physical accuracy through physically based rendering. This work directly addresses the critical challenge of training robust deep neural networks for computer vision tasks, particularly in autonomous driving applications where real-world annotated data is scarce or expensive to obtain. By bridging the gap between synthetic and real-world data, her research has significant implications for improving the performance and safety of automotive perception systems. Tsirikoglou’s approach not only enhances data diversity but also ensures that synthetic images maintain the visual fidelity necessary for effective model training, marking a notable achievement in the field of synthetic data generation.
Research Focus
Key Achievements
Top Papers
- 1