A Neural CDE driven by a Savitzky-Golay smoothed control path on SO(3) forecasts rotations more accurately than GRU and spline-CDE baselines on real tracking data.
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
-
Continuous-Time SO(3) Forecasting with Savitzky--Golay Neural Controlled Differential Equations
A Neural CDE driven by a Savitzky-Golay smoothed control path on SO(3) forecasts rotations more accurately than GRU and spline-CDE baselines on real tracking data.