3 papers
cs.CV2025
Temporal Object Captioning for Street Scene Videos from LiDAR Tracks
Vignesh Gopinathan, Urs Zimmermann, Michael Arnold +1
Video captioning models have seen notable advancements in recent years, especially with regard to their ability to capture temporal information. While many research efforts have fo…
cs.CV2025
Adverse Weather Conditions Augmentation of LiDAR Scenes with Latent Diffusion Models
Andrea Matteazzi, Pascal Colling, Michael Arnold +1
LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rare…
cs.CV2024
A Preprocessing and Postprocessing Voxel-based Method for LiDAR Semantic Segmentation Improvement in Long Distance
Andrea Matteazzi, Pascal Colling, Michael Arnold +1
In recent years considerable research in LiDAR semantic segmentation was conducted, introducing several new state of the art models. However, most research focuses on single-scan p…