LOMA uses language priors from a vision-language model and a tri-plane Mamba fusion block to improve monocular 3D semantic occupancy prediction, reporting higher occupancy IoU on SemanticKITTI and SSCBench-KITTI360.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LOMA: Language-assisted Semantic Occupancy Network via Triplane Mamba
LOMA uses language priors from a vision-language model and a tri-plane Mamba fusion block to improve monocular 3D semantic occupancy prediction, reporting higher occupancy IoU on SemanticKITTI and SSCBench-KITTI360.