Research map / Architectures and efficiency / Pruning and efficient tuning
Compressed Sensing MRI Using a Recursive Dilated Network
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| increase recursions per block from 1 to 5 (ablation) | RDN-5B-3D · Brain MRI 30% Cartesian | PSNR: 39.91 -> 41.09 | Helped |
| increase recursions per block from 1 to 5 (ablation) | RDN-5B-3D · Brain MRI 30% Cartesian | SSIM: 0.975 -> 0.981 | Helped |
| add dilated convolutions to RDN (ablation) | RDN · Brain MRI 30% Cartesian | PSNR/SSIM | Helped |
| use feature-extraction shortcut to all blocks instead of ResNet shortcut (ablation) | recursive network without dilation · Brain MRI 30% Cartesian | PSNR/SSIM | Helped |
| replace plain CNN recursion with ResNet recursion (ablation) | recursive network · Brain MRI 30% Cartesian | PSNR/SSIM | Helped |
| RDN with 18K parameters vs DC-CNN 38K | RDN · Brain MRI 30% Cartesian | PSNR/SSIM | No clear effect |
Closest papers by meaning
- Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction (NeurIPS 2019 · similarity 0.93)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.89)
- UFC-Net: Unrolling Fixed-point Continuous Network for Deep Compressive Sensing (CVPR 2024 · similarity 0.86)
- Multi-Cross Sampling and Frequency-Division Reconstruction for Image Compressed Sensing (AAAI 2024 · similarity 0.86)
- Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms (NeurIPS 2024 · similarity 0.85)
- Fast MRI for All: Bridging Access Gaps by Training without Raw Data (NeurIPS 2025 · similarity 0.85)
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.