atlas

Research map / 3D vision / Face and shape

An Unsupervised Learning Model for Deformable Medical Image Registration

CVPR 2018 · 3D vision › Face and shape · approach: Learned mesh and geometric representations · 675 citations (OpenAlex)

Read the paperCheck 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
Replace pair-specific iterative registration with a learned CNN registration functionVoxelMorph · Brain MRI test setAvg. Dice: 0.749 (0.135) -> 0.742 (0.139)No clear effect
Replace pair-specific iterative registration with a learned CNN registration functionVoxelMorph-1 vs ANTs · Brain MRI test setCPU sec: 9059 (2023) -> 57(1)Helped
Use the larger decoder architecture (ablation)VoxelMorph-1 · Brain MRI test setAvg. Dice: 0.742 (0.139) -> 0.750 (0.137)Helped
Use the larger decoder architecture (ablation)VoxelMorph-1 · Brain MRI test setCPU sec: 57(1) -> 144 (1)Hurt
Train on ABIDE scans only instead of all datasetsVoxelMorph-1 · ABIDE test scansAvg. Dice: 0.715(0.140) -> 0.729(0.142)Helped
Train on ABIDE scans only instead of all datasetsVoxelMorph-2 · ABIDE test scansAvg. Dice: 0.718(0.141) -> 0.734(0.140)Helped
Set the smoothing regularization parameter to zero (ablation)VoxelMorph · Brain MRI validation setAvg. DiceHelped
Vary the smoothing regularization parameter (ablation)VoxelMorph · Brain MRI validation setAvg. DiceNo clear effect

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