AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DiffuseMorph: Unsupervised Deformable Image Registration Using Diffusion Model

Boah Kim, Inhwa Han, Jong Chul Ye

ECCV 2022 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 121 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
increase registration loss weight lambda from 2 to 10 (ablation)DiffuseMorph · OASIS-3 brain MR registrationDice: 0.736 -> 0.756Improved
increase registration loss weight lambda from 2 to 10 (ablation)DiffuseMorph · OASIS-3 brain MR registrationnon-positive Jacobian (%): 0.498 -> 0.505Hurt
use diffusion-based latent features instead of VM in facial registrationVoxelMorph deformation network · RaFD facial expression registrationNMSE x10^-1: 0.047 -> 0.032Improved
use DiffuseMorph instead of VM-diff in facial registrationVM-diff · RaFD facial expression registrationSSIM: 0.957 -> 0.964Improved
use DiffuseMorph instead of VM-diff on foldingVM-diff · RaFD facial expression registrationnon-positive Jacobian (%): 0.014 -> 0.017No clear effect
use DiffuseMorph instead of VM in cardiac registrationVM · ACDC cardiac MR registrationDice: 0.787 -> 0.802Improved
use DiffuseMorph instead of VM-diff in cardiac registrationVM-diff · ACDC cardiac MR registrationnon-positive Jacobian (%): 0.291 -> 0.161Improved
scale the latent score feature instead of scaling or integrating the field for continuous deformationVM-diff · ACDC cardiac MR continuous deformationPSNR (dB): 29.481 -> 30.725Improved
scale the latent score feature instead of scaling the fieldVM · ACDC cardiac MR continuous deformationPSNR (dB): 30.678 -> 30.725No clear effect
use DiffuseMorph instead of VM in brain registrationVM · OASIS-3 brain MR registrationDice: 0.749 -> 0.756Improved
use DiffuseMorph instead of SyN in brain registrationSyN · OASIS-3 brain MR registrationDice: 0.752 -> 0.756Improved
use DiffuseMorph instead of MSDIRNetMSDIRNet · OASIS-3 brain MR registrationnon-positive Jacobian (%): 0.804 -> 0.505Improved

Later papers that compared with this method

2 later accepted papers report DiffuseMorph as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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