Tarabini Marco
Papers
1
Total Citations
2
H-Index
1
About
Marco Tarabini is a researcher specializing in computer vision and deep learning, with a particular focus on 3D object pose estimation and spatial localization. His most notable contribution is the development of the "3DOPE-DL" framework, a deep learning-based approach for 3D object pose estimation that addresses critical challenges in accuracy and uncertainty quantification. In his 2020 work, Tarabini conducted a rigorous evaluation of the DenseFusion architecture, analyzing its precision in estimating object orientation and position using the benchmark Yale-Carnegie-Berkeley Video Dataset. By calculating the Average Euclidean Distance between predicted and ground-truth poses, he provided valuable insights into the reliability of deep learning methods for real-world robotic and augmented reality applications. While his work has garnered 2 citations, its significance lies in establishing a systematic methodology for uncertainty assessment in 3D pose estimation—a crucial step toward deploying these systems in safety-critical environments. Tarabini’s research bridges the gap between theoretical deep learning models and practical deployment, offering a foundation for future work in robust object localization. His contributions are particularly relevant for students and researchers exploring uncertainty-aware computer vision systems.
Research Focus
Key Achievements
Top Papers
- 1