AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

SDUM: A Scalable Deep Unrolled Model for Universal Cardiac MRI Reconstruction

Puyang Wang, Pengfei Guo, Keyi Chai, Jinyuan Zhou, Daguang Xu, Shanshan Jiang

ECCV 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Zero-shot robustness and transfer · 0 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
use Restormer backbone instead of U-Net (ablation)SDUM T=6 · CMRxRecon2025 Regular Task 1PSNR (dB): 28.734 -> 32.090Improved
use 2 down-sampling layers instead of 4 (ablation)SDUM T=6 · CMRxRecon2025 Regular Task 1PSNR (dB): 31.544 -> 32.090Improved
use 2 down-sampling layers instead of 1 (ablation)SDUM T=6 · CMRxRecon2025 Regular Task 1PSNR (dB): Training failedImproved
widen single cascade from 7.2M to 78.7M params (ablation)SDUM T=1 · CMRxRecon2025 Regular Task 1PSNR (dB): 27.605 -> 28.978Improved
widen single cascade beyond 42.2M params (ablation)SDUM T=1 · CMRxRecon2025 Regular Task 1PSNR (dB): 28.728 -> 28.978No clear effect
use per-cascade CSME instead of single shared CSME (ablation)SDUM · CMRxRecon2025 Regular Task 1PSNR (dB): 29.694 -> 30.205Improved
use SWDC instead of simple learnable DC (ablation)SDUM T=6 · CMRxRecon2025 Regular Task 1PSNR (dB): 31.661 -> 32.090Improved
use SWDC instead of non-sampling-aware weighted DC (ablation)SDUM T=6 · CMRxRecon2025 Regular Task 1PSNR (dB): 31.787 -> 32.090Improved
add universal conditioning (ablation)SDUM T=1 Iter=3 · CMRxRecon2025 Regular Task 1PSNR (dB): 29.693 -> 30.071Improved
use 3 cascades instead of 3 iterations of one cascade (ablation)SDUM · CMRxRecon2025 Regular Task 1PSNR (dB): 30.071 -> 30.205Improved
increase unrolled depth from T=1 to T=18SDUM · CMRxRecon2025 Regular Task 1PSNR (dB): 28.73 -> 33.18Improved
increase depth from T=10 to T=18SDUM · CMRxRecon2025 Regular Task 1PSNR (dB): 32.54 -> 33.18Improved

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