3 papers
cs.LG2025
Diffusion-Based Generation and Imputation of Driving Scenarios from Limited Vehicle CAN Data
Julian Ripper, Ousama Esbel, Rafael Fietzek +2
Training deep learning methods on small time series datasets that also include corrupted samples is challenging. Diffusion models have shown to be effective to generate realistic a…
cs.CV2025
DeSPITE: Exploring Contrastive Deep Skeleton-Pointcloud-IMU-Text Embeddings for Advanced Point Cloud Human Activity Understanding
Thomas Kreutz, Max Mühlhäuser, Alejandro Sanchez Guinea
Despite LiDAR (Light Detection and Ranging) being an effective privacy-preserving alternative to RGB cameras to perceive human activities, it remains largely underexplored in the c…
cs.LG2025
Whenever, Wherever: Towards Orchestrating Crowd Simulations with Spatio-Temporal Spawn Dynamics
Thomas Kreutz, Max Mühlhäuser, Alejandro Sanchez Guinea
Realistic crowd simulations are essential for immersive virtual environments, relying on both individual behaviors (microscopic dynamics) and overall crowd patterns (macroscopic ch…