A neural ODE block used as the refinement module in GMFlow improves reported optical flow accuracy over the original GRU-based model while using a single outer refinement step.
Learn- ing long-term dependencies with gradient descent is difficult
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
background 1representative citing papers
citing papers explorer
-
Learning Optical Flow Field via Neural Ordinary Differential Equation
A neural ODE block used as the refinement module in GMFlow improves reported optical flow accuracy over the original GRU-based model while using a single outer refinement step.