8 citations
2 papers
cs.CV2026
SelfOccFlow: Towards end-to-end self-supervised 3D Occupancy Flow prediction
Xavier Timoneda, Markus Herb, Fabian Duerr +1
Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jo…
cs.LG2026★ 8 cited
Latent Matters: Learning Deep State-Space Models
Alexej Klushyn, Richard Kurle, Maximilian Soelch +2
Deep state-space models (DSSMs) enable temporal predictions by learning the underlying dynamics of observed sequence data. They are often trained by maximising the evidence lower b…