Research map / Label-efficient and robust learning / Self-supervised and contrastive
Reference-Free Meta-Learning for Generalized Implicit Neural Representation in Efficient MRI Reconstruction
Haonan Zhang, Qing Wu, Xuanyu Tian, Bowen Li, Yuyao Zhang, Hongjiang Wei
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add IPOD meta-initialization | SIREN · MoDL brain Cartesian AF 4 | PSNR: 41.77 -> 53.69 | Improved |
| add IPOD meta-initialization | DINER · MoDL brain Cartesian AF 4 | PSNR: 40.08 -> 52.13 | Improved |
| add IPOD meta-initialization | HASH · fastMRI brain Cartesian AF 3 | PSNR: 60.68 -> 59.88 | Hurt |
| add IPOD meta-initialization | HASH · fastMRI brain Radial AF 10/14 | PSNR: 38.95 -> 39.26 | No clear effect |
| add IPOD meta-initialization | DINER · fastMRI brain Cartesian AF 3 | PSNR: 58.58 -> 58.98 | No clear effect |
| add IPOD meta-initialization | HASH · 3D reconstruction Poisson AF 6 | PSNR: 31.52 -> 33.21 | Improved |
| add IPOD initialization | INR backbones · reconstruction time | speedup: 2x to 3x | Improved |
| add adaptive loss-based task weighting in meta-update (ablation) | IPOD-SIREN · MoDL brain Cartesian AF 4 | PSNR: 36.38 -> 37.14 | Improved |
| meta-train on all sampling patterns and anatomies instead of Cartesian only (ablation) | IPOD-SIREN · radial undersampling iter 100 | PSNR: 26.80 -> 30.97 | Improved |
| meta-train on brain and knee instead of brain only (ablation) | IPOD-SIREN · fastMRI knee iter 1000 | PSNR: 33.14 -> 34.74 | Improved |
| meta-train on Cartesian only vs random init (ablation) | SIREN · radial undersampling iter 1000 | PSNR: 31.47 -> 32.92 | Improved |
| increase meta-learning epochs K (ablation) | IPOD-SIREN · fastMRI brain AF 4 | PSNR | Improved |
Closest papers by meaning
- D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction (NeurIPS 2025 · similarity 0.87)
- Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data (ICLR 2025 · similarity 0.85)
- Anatomical Consistency and Adaptive Prior-informed Transformation for Multi-contrast MR Image Synthesis via Diffusion Model (CVPR 2025 · similarity 0.85)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.85)
- Autoregressive Image Diffusion: Generation of Image Sequence and Application in MRI (NeurIPS 2024 · similarity 0.84)
- Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation (ICLR 2025 · similarity 0.84)
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.
