Papers
1
Total Citations
8
H-Index
1
About
P. Arnaud is a leading researcher in computer vision and geometric deep learning, with a focus on bridging the gap between raw 3D sensor data and structured digital models. Their most notable contribution is the development of SMA-Net, a pioneering deep learning framework that simultaneously identifies and fits CAD models from unstructured point clouds. This work, published in 2022 and already garnering 8 citations, addresses a critical challenge in reverse engineering and robotic perception by enabling machines to parse complex real-world scenes into precise, editable CAD primitives. Arnaud's research has significant implications for autonomous manufacturing, digital twin creation, and augmented reality, where rapid and accurate 3D understanding is essential. By integrating neural networks with geometric reasoning, they have advanced the field of 3D shape analysis, offering a scalable solution for converting noisy scans into clean, parametric models. Their work stands out for its practical impact, providing a foundation for future systems that can interpret and interact with physical environments in a semantically meaningful way.
Research Focus
Key Achievements
Top Papers
- 1