A parameter-shared residual MLP with per-point normalization reaches competitive point cloud accuracy at 0.58M parameters and runs 3.7x faster on an FPGA than the CPU baseline.
Colored Point Cloud Registration Revisited
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PointODE: Lightweight Point Cloud Learning with Neural Ordinary Differential Equations on Edge
A parameter-shared residual MLP with per-point normalization reaches competitive point cloud accuracy at 0.58M parameters and runs 3.7x faster on an FPGA than the CPU baseline.