MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments

RoCaRS: Robust Camera-Radar BEV Segmentation for Sensor Failure Scenarios

Boosting Cross-spectral Unsupervised Domain Adaptation for Thermal Semantic Segmentation

Leveraging Camera-Based Methods for Enhanced Feature-to-World Mapping

Efficient Occupancy Prediction with Instance-level Attention

SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Driving

UMHE: Unsupervised Multispectral Homography Estimation

T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction

Instant Domain Augmentation for LiDAR Semantic Segmentation

TransDSSL: Transformer Based Depth Estimation via Self-Supervised Learning