Nick Michiels
Papers
2
Total Citations
22
H-Index
2
About
Nick Michiels is a leading researcher at the intersection of computer vision, computer graphics, and manufacturing, with a core focus on synthetic data generation and robotic perception. His most impactful work, "CAD2Render: A Modular Toolkit for GPU-accelerated Photorealistic Synthetic Data Generation for the Manufacturing Industry" (2023, 18 citations), addresses a critical bottleneck in industrial AI: the scarcity of labeled training data. By enabling the rapid creation of photorealistic synthetic images from CAD models, Michiels provides a scalable solution for training machine learning models in quality control and assembly verification, directly bridging the gap between simulation and real-world deployment. Building on this foundation, his recent work "DistillGrasp: Integrating Features Correlation With Knowledge Distillation for Depth Completion of Transparent Objects" (2024, 4 citations) tackles the notoriously difficult problem of robotic manipulation of transparent objects. By pioneering a knowledge distillation framework that correlates visual features to complete missing depth data, Michiels advances the robustness of grasping systems in complex, real-world environments. His contributions are not only technically rigorous but also highly practical, offering modular, industry-ready tools that accelerate the adoption of AI in manufacturing and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2