LiteViLNet fuses vision and LiDAR via lightweight encoders and cross-modal modules to reach 96.36% MaxF on KITTI Road with 14.04M parameters at 163.79 FPS on RTX 4060 Ti.
Cross-view transformers for real-time map-view semantic segmentation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
No citing papers match the current filters.