AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Low-Level Dataset Distillation for Medical Image Enhancement

Fengzhi Xu, Ziyuan Yang, Mengyu Sun, Joey Tianyi Zhou, Yi Zhang

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 1 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 shared anatomical prior initialization instead of random noise (ablation)Ours (IPP=5) · CT x4 SRPSNR: 11.30 -> 34.57Improved
add the shared anatomical prior initialization instead of random noise (ablation)Ours (IPP=1) · CT x4 SRPSNR: 11.54 -> 32.93Improved
add the pixel-level fidelity preservation step (ablation)Ours (IPP=5) · CT x4 SRPSNR: 30.55 -> 34.45Improved
add the pixel-level fidelity preservation step (ablation)Ours (IPP=1) · CT x4 SRPSNR: 16.95 -> 32.73Improved
increase images per patient from IPP=1 to IPP=5 (ablation)Ours · CT x4 SR NRI=5PSNR: 32.73 -> 34.45Improved
increase images per patient from IPP=1 to IPP=5 (ablation)Ours · MRI x2 SR NRI=5PSNR: 26.95 -> 28.16Improved
increase images per patient from IPP=1 to IPP=5 (ablation)Ours · CT low-dose restoration NRI=5PSNR: 28.00 -> 28.38Improved
increase random real images NRI from 5 to 10 (ablation)Ours (IPP=5) · CT x4 SRPSNR: 34.45 -> 34.57Improved
replace K-Center coreset with distilled dataOurs (IPP=5) · CT x4 SR large-scale (48 patients) NRI=5PSNR: 31.75 -> 36.08Improved
distill with SRCNN and train EDSR instead of K-Center coresetOurs (IPP=5) · CT x4 SR cross-architecturePSNR: 34.13 -> 35.48Improved
distill with SRCNN and train SCTSRN instead of K-Center coresetOurs (IPP=5) · CT x4 SR cross-architecturePSNR: 34.47 -> 34.52No clear effect
replace K-Center coreset with distilled data for restorationOurs (IPP=5) · CT low-dose restoration NRI=10PSNR: 28.11 -> 28.38Improved

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