Research map / Video / Video segmentation and tracking
Zero-shot Implicit Neural Manifold Representation (INMR) for Ultra-high Temporal Resolution Dynamic MRI
Jie Feng, Rui Luo, Tian Zeng, Xin Shen, Haikun Qi, Yuyao Zhang, Dong Liang, 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 |
|---|---|---|---|
| use learnable manifold vectors instead of fixed temporal indices (stINR), 1 cardiac cycle (ablation) | INR dynamic MRI · simulated cardiac | PSNR (dB): 29.78 -> 31.77 PSNR; 0.913 -> 0.861 SSIM | Mixed |
| train INMR on 4 cardiac cycles instead of 1 (ablation) | INMR · simulated cardiac | PSNR (dB): 31.77 -> 33.54 | Improved |
| use manifold vectors instead of fixed indices (ablation) | INR dynamic MRI · simulated cardiac | GPU memory (MB): 22874 -> 10914 | Improved |
| add spatial C2F optimization (ablation) | INMR · simulated cardiac | PSNR (dB): 33.14 -> 33.67 | Improved |
| add temporal C2F (Gaussian perturbation annealing) (ablation) | INMR · simulated cardiac | PSNR (dB): 33.14 -> 33.36 | Improved |
| add both spatial and temporal C2F (ablation) | INMR · simulated cardiac | PSNR (dB): 33.14 -> 33.93 | Improved |
| increase manifold dimension from 2 to 8 (ablation) | INMR · simulated cardiac | PSNR (dB): 31.82 -> 33.93 | Improved |
| increase manifold dimension from 8 to 16 (ablation) | INMR · simulated cardiac | PSNR (dB): 33.93 -> 33.62 | No clear effect |
| add smoothness regularization (lambda 0 -> 10) (ablation) | INMR · simulated cardiac | PSNR (dB): 29.91 -> 33.93 | Improved |
| raise lambda from 10 to 20 (ablation) | INMR · simulated cardiac | PSNR (dB): 33.93 -> 33.24 | Hurt |
| INMR instead of FMLP | unsupervised INR reconstruction · simulated cardiac reconstruction time | time (s): 2446.17 -> 219.11 | Improved |
Closest papers by meaning
- Spatiotemporal-Aware Neural Fields for Dynamic CT Reconstruction (AAAI 2025 · similarity 0.85)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.84)
- D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction (NeurIPS 2025 · similarity 0.83)
- A scalable generative model for dynamical system reconstruction from neuroimaging data (NeurIPS 2024 · similarity 0.83)
- MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation (NeurIPS 2026 · similarity 0.83)
- Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation (ICLR 2025 · similarity 0.82)
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.
