A lookup table that stores precomputed outputs of the per-point MLP can replace network inference in point-wise point cloud models, achieving near-identical accuracy with much lower CPU latency.
However, it still gains impressive results on 3D vision tasks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables
A lookup table that stores precomputed outputs of the per-point MLP can replace network inference in point-wise point cloud models, achieving near-identical accuracy with much lower CPU latency.