A hybrid Mamba-Swin network with a depth-weighted and bird's-eye-view-constrained loss improves sparse LiDAR point cloud upsampling over prior range-image methods.
Efficient deep super-resolution of voxelized point cloud in geometry compression,
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
unclear 1representative citing papers
citing papers explorer
-
SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving
A hybrid Mamba-Swin network with a depth-weighted and bird's-eye-view-constrained loss improves sparse LiDAR point cloud upsampling over prior range-image methods.