atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration

CVPR 2022 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural ODE training and analysis · 36 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Set λ1 to 2 instead of 2.5 (ablation)NODEO · OASISAvg. Dice (28): 0.778 ± 0.026 -> 0.779 ± 0.026Helped
Set λ1 to 2 instead of 2.5 (ablation)NODEO · CANDIAvg. Dice (28): 0.801 ± 0.011 -> 0.802 ± 0.011Helped
Set λ1 to 2 instead of 2.5 (ablation)NODEO · CANDIAvg. Dice (32): 0.760 ± 0.011 -> 0.760 ± 0.011No clear effect
Add Gaussian smoothing and the negative-Jacobian regularizer (ablation)NODEO · 2D illustrative image registrationfolding / diffeomorphismHelped
Add Gaussian smoothing (ablation)NODEO · 2D illustrative image registrationspatial smoothnessHelped
Add the negative-Jacobian regularizer (ablation)NODEO · 2D illustrative image registrationdiffeomorphismHelped
Use a time-varying system with explicit time embedding instead of a time-invariant system (ablation)NODEO · 2D multiple-image registrationregistration qualityHelped
Down-sample the image before the network (ablation)NODEO · Image-pair registrationruntime: 1/3Helped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy