← Search

Xavier Timoneda

2 accepted papers

2026

SelfOccFlow: Towards End-to-End Self-Supervised 3D Occupancy Flow Prediction

RA-L 2026

Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D occupancy and flow annotations, velocity labels from bounding b

Cited by 0SourceScholar
2024

Multi-modal NeRF Self-Supervision for LiDAR Semantic Segmentation

IROS 2024

LiDAR Semantic Segmentation is a fundamental task in autonomous driving perception consisting of associating each LiDAR point to a semantic label. Fully-supervised models have widely tackled this task, but they require labels for each scan, which either limits their domain or requires impractical am

Cited by 5SourceScholar