Abstract
Autonomous driving is advancing rapidly, fueled by improvements in sensor technology and artificial intelligence (AI). Lidar-captured point clouds are crucial for these systems, offering precise spatial data and detailed environmental representations. Data are essential for developing and validating robust AI-based systems. However, obtaining real-world data is costly, and capturing specific scenarios, especially dangerous or rare cases, is impractical. As a result, synthetic point cloud generation is emerging as a promising alternative. Despite increasing interest and techniques, there is no comprehensive survey on synthetic point cloud generation for autonomous driving. This article addresses this gap by exploring the challenges in generating synthetic point clouds, outlining the methods used, and cataloging available datasets. This survey aims to provide a foundational understanding of the state of the art in synthetic point cloud generation, promoting further research in this critical area of autonomous driving technology.
Aitor Iglesias
PhD Student
My research focuses on enhancing the reliability of Autonomous Driving functions using Machine Learning techniques.
Nerea Aranjuelo Ansa
Former PhD student
My research focuses on machine learning and computer vision for multimodal perception systems.
Ignacio Arganda-Carreras
Ikerbasque Research Associate Professor
My research interests include image processing, computer vision, and deep learning for biomedical applications.