LRS4Fusion fuses cameras and LiDAR in a fully sparse voxel representation with self-supervised temporal pre-training, achieving 52.61 mAP for detection out to 250 meters.
Monoscene: Monoc- ular 3d semantic scene completion
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Self-Supervised Sparse Sensor Fusion for Long Range Perception
LRS4Fusion fuses cameras and LiDAR in a fully sparse voxel representation with self-supervised temporal pre-training, achieving 52.61 mAP for detection out to 250 meters.