SliceSemOcc improves 3D semantic occupancy prediction by slicing voxel features into global and local height bands and applying per-height channel attention, yielding modest mIoU gains on nuScenes benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SliceSemOcc: Vertical Slice Based Multimodal 3D Semantic Occupancy Representation
SliceSemOcc improves 3D semantic occupancy prediction by slicing voxel features into global and local height bands and applying per-height channel attention, yielding modest mIoU gains on nuScenes benchmarks.