Research map / Image generation / Super-resolution
PINGS-X: Physics-Informed Normalized Gaussian Splatting with Axes Alignment for Efficient Super-Resolution of 4D Flow MRI
Sun Jo, Seok Young Hong, Jinhyun Kim, Seungmin Kang, Ahjin Choi, Don-Gwan An, Simon Song, Je Hyeong Hong
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 |
|---|---|---|---|
| remove normalization from Gaussian weights (use unnormalized sum) (ablation) | PINGS-X · synthetic CFD (3 cases) | convergence: converges -> NC (non-convergence) | Improved |
| add axes-alignment (diagonal covariance) (ablation) | PINGS-X · Y-shaped channel | training time: 23.3 -> 4.8 min | Improved |
| add axes-alignment (ablation) | PINGS-X · Lid-driven cavity | Relative L2 error (%): 1.01 -> 1.13 | Hurt |
| add Gaussian merging (ablation) | PINGS-X · Lid-driven cavity | Relative L2 error (%): 1.38 -> 1.13 | Improved |
| add Gaussian merging (ablation) | PINGS-X · Y-shaped channel | Relative L2 error (%): 1.66 -> 2.62 | Hurt |
| normalized (PINGS) vs unnormalized (PIGS) Gaussians (ablation) | Gaussian splatting · Rosenbrock fit, 600 Gaussians | Relative error (%): 3.53 -> 0.04 | Improved |
| vary number of initial Gaussians 200 to 1600 (ablation) | PINGS-X · lid-driven cavity | Relative L2 error (%): 1.13 vs 1.33 at 1600 | No clear effect |
| PINGS-X vs best baseline on 4D flow MRI x8 | PINGS-X · carotid x8 | Relative L2 error (%): 10.63 -> 8.98 | Improved |
Closest papers by meaning
- Adaptive Anisotropic Gaussian Splatting for Multi-contrast MRI Arbitrary-Scale Super-Resolution with Anatomy Guidance (CVPR 2026 · similarity 0.87)
- MiCo: Microstructure-Consistent Flow Matching for Diffusion MRI Angular Super-Resolution (NeurIPS 2026 · similarity 0.87)
- X2-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction (ICCV 2025 · similarity 0.85)
- Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle (CVPR 2024 · similarity 0.84)
- 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering (CVPR 2024 · similarity 0.84)
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction (NeurIPS 2024 · 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.
