AI Paper Atlas

Research map / Image generation / Super-resolution

Decomposition-Based Variational Network for Multi-Contrast MRI Super-Resolution and Reconstruction

Pengcheng Lei, Faming Fang, Guixu Zhang, Tieyong Zeng

ICCV 2023 · Image generation › Super-resolution · approach: CNN and transformer SR architectures · 50 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 common/unique decomposition of the reference image (ablation)MC-VarNet-S · IXI-T2 SR x4PSNR: 41.32 -> 41.71Improved
use decomposition-based fusion instead of concatenation fusion (ablation)MC-VarNet-S · IXI-T2 SR x4PSNR: 41.05 -> 41.71Improved
use a reference contrast at all instead of single contrast (ablation)MC-VarNet-S · IXI-T2 SR x4PSNR: 33.50 -> 41.71Improved
add data consistency layer (DCL) (ablation)MC-VarNet-S · IXI-T2 SR x4PSNR: 41.25 -> 41.71Improved
use modified U-Net denoiser instead of ResNet (ablation)MC-VarNet-S · IXI-T2 SR x4PSNR: 41.21 -> 41.71Improved
add channel expansion (ablation)MC-VarNet-S · BrainTS-T2 SR x4PSNR: 38.53 -> 39.81Improved
add channel expansion (ablation)MC-VarNet-S · BrainTS-T2 reconstruction x4PSNR: 39.28 -> 41.60Improved
increase iteration stages from T=1 to T=4 (ablation)MC-VarNet · BrainTS-T2PSNR: +3.35dB (reconstruction), +0.72dB (SR)Improved

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