Research map / 3D vision / Gaussian splatting
Super-Resolution and Sparse View CT Reconstruction
Guangming Zang, Mohamed Aly, Ramzi Idoughi, Peter Wonka, Wolfgang Heidrich
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 |
|---|---|---|---|
| replace SAD prior with 3D structure tensor prior (ablation) | PSART · Simulated 3D Fresnel zone plate (noise sigma=2, 6.4x downsampled projections) | PSNR: 22.6293 -> 24.8331 | Improved |
| replace SAD prior with 3D structure tensor prior (ablation) | PSART · Simulated 3D Fresnel zone plate (noise sigma=2, 6.4x downsampled projections) | SSIM: 0.9781 -> 0.9864 | Improved |
| use SART with SAD prior instead of CG with TV prior (ablation) | proximal CT framework · Simulated 3D Fresnel zone plate (noise sigma=2, 6.4x downsampled projections) | PSNR: 22.0659 -> 22.6293 | Improved |
| add a regularizing prior (STP) to plain SART | SART · Simulated 3D Fresnel zone plate (noise sigma=2, 6.4x downsampled projections) | PSNR: 19.5440 -> 24.8331 | Improved |
| add proximal regularized framework to FDK | FDK · Simulated 3D Fresnel zone plate (noise sigma=2, 6.4x downsampled projections) | PSNR: 17.5978 -> 24.8331 | Improved |
| use SART instead of CG as data-term solver with TV prior (ablation) | proximal CT framework · Shepp-Logan and real rose sparse view (30-90 projections) | PSNR and SSIM | Improved |
| use STP instead of SAD prior (ablation) | PSART · Zone plate convergence | RMSE: slower convergence, lower final RMSE | Mixed |
| use SART-based PSART instead of PCG-TV (ablation) | proximal CT framework · Zone plate running time | RMSE vs running time | Improved |
Closest papers by meaning
- Tomographic Sparse View Selection Using the View Covariance Loss (TPAMI 2025 · similarity 0.88)
- Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction (CVPR 2026 · similarity 0.87)
- QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction (CVPR 2024 · similarity 0.87)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.86)
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction (NeurIPS 2024 · similarity 0.85)
- Weakly Convex Regularisers for Inverse Problems: Convergence of Critical Points and Primal-Dual Optimisation (ICML 2024 · 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.
