Research map / 3D vision / Depth and stereo
Unsupervised Motion-Compensated Decomposition for Cardiac MRI Reconstruction via Neural Representation
Xuanyu Tian, Lixuan Chen, Qing Wu, Xiao Wang, Jie Feng, 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 DVF regularization loss L_DVF (ablation) | MoCo-INR · OCMR GA radial 69.3x | PSNR: 34.42 -> 37.75 | Improved |
| add DVF regularization loss L_DVF (ablation) | MoCo-INR · OCMR GA radial 69.3x | SSIM: 0.895 -> 0.940 | Improved |
| add coarse-to-fine hash encoding learning (ablation) | MoCo-INR · OCMR GA radial 69.3x | PSNR: 35.51 -> 37.75 | Improved |
| add coarse-to-fine hash encoding learning (ablation) | MoCo-INR · OCMR GA radial 69.3x | SSIM: 0.926 -> 0.940 | Improved |
| replace MLP decoder with three-layer CNN decoder (ablation) | MoCo-INR · OCMR VISTA 20x | PSNR | Improved |
| replace ST-INR (L&S) with MoCo-INR | ST-INR (L&S) · OCMR VISTA 20x | PSNR: 36.26 -> 39.53 | Improved |
| replace ST-INR (L&S) with MoCo-INR | ST-INR (L&S) · OCMR GA radial 69.3x | PSNR: 33.92 -> 37.75 | Improved |
| replace ST-INR (L&S) with MoCo-INR | ST-INR (L&S) · OCMR VISTA 12x | SSIM: 0.972 -> 0.971 | No clear effect |
| replace ST-INR (L&S) with MoCo-INR | ST-INR (L&S) · Retrospective GA radial runtime | runtime (min): 10.9 -> 5.5 | Improved |
| replace ST-INR (L&S) with MoCo-INR | ST-INR (L&S) · Prospective VISTA runtime | runtime (min): 6.7 -> 3.4 | Improved |
| drop low-rank and sparsity constraints from ST-INR (ablation) | ST-INR · OCMR VISTA 12x | PSNR: 41.35 -> 36.31 | Hurt |
| replace TDDIP with MoCo-INR | TDDIP · Prospective VISTA runtime | runtime (min): 19.3 -> 3.4 | Improved |
Closest papers by meaning
- Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation (ICLR 2025 · similarity 0.87)
- Fully Convolutional Slice-to-Volume Reconstruction for Single-Stack MRI (CVPR 2024 · similarity 0.84)
- Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI (CVPR 2024 · similarity 0.83)
- Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding (NeurIPS 2024 · similarity 0.83)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.83)
- D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction (NeurIPS 2025 · similarity 0.83)
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.
