AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Bigger Isn’t Always Better: Towards a General Prior for Medical Image Reconstruction

Lukas Glaszner, Martin Zach, Thomas Pock

IJCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion posterior sampling · 2 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
add the self-attention block (d=4* vs d=4) (ablation)score model · CORPD 4x Gaussian 1D, PC samplingPSNR: 32.52 -> 32.81Hurt
shrink network to d=1 (smallest receptive field) (ablation)score model, fastMRI-trained · CORPDFS (OOD) 4x Gaussian 1D, PCPSNR: 31.08 -> 31.70Improved
shrink network to d=1 (ablation)score model, fastMRI-trained · CORPD (ID) 4x Gaussian 1D, PCPSNR: 32.52 -> 32.19Mixed
shrink network to d=1 (ablation)score model, fastMRI-trained · CORPDFS (OOD) 8x Gaussian 1D, PCPSNR: 29.52 -> 30.24Improved
train on natural images (CelebA-HQ) instead of fastMRI (ablation)score model d=1 · CORPDFS (OOD) 4x Gaussian 1D, PCPSNR: 31.70 -> 31.86Improved
train on natural images (CelebA-HQ) instead of fastMRI (ablation)score model d=1 · CORPD (ID) 4x Gaussian 1D, PCPSNR: 32.19 -> 32.61Improved
train on CelebA-HQ instead of fastMRI (ablation)score model d=4* · Brain MRI (OOD) 4x Gaussian 1D, PCPSNR: 32.69 -> 32.10Hurt
shrink network to d=1 with Poisson 15x mask, CelebA-trained (ablation)score model · CORPD Poisson 15x, PCPSNR: 30.37 -> 28.62Hurt
shrink network on CT (d=4* to d=1) (ablation)score model, CT-trained · Thorax CT (ID) 60 viewsPSNR: 36.29 -> 36.14No clear effect
use diffusion prior instead of TV (ablation)score model d=4* · Thorax CT 60 viewsPSNR: 23.21 -> 36.29Improved
reduce depth from d=4* to d=1 (inference cost) (ablation)score model, PC sampling · reconstruction time per sliceseconds: 84.4 -> 39.23Improved
lower data-consistency weight lambda (near 0) for CelebA-trained networks (ablation)score model PC sampling · CORPD slicequalitativeHurt

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