Research map / 3D vision / Face and shape
TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging
Qinglei Cao, Ziyao Tang, Xiaoqin Tang
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 TPSE structural encoding (ablation) | baseline INR · Chest (3D cone-beam, 20 views) | PSNR: 28.00 -> 28.65 | Improved |
| add TPVS target prior-guided sampling (ablation) | baseline INR · Chest (3D cone-beam, 20 views) | PSNR: 28.00 -> 32.76 | Improved |
| add both TPSE and TPVS (ablation) | baseline INR · Chest (3D cone-beam, 20 views) | PSNR: 28.00 -> 35.55 | Improved |
| add TPSE and TPVS to baseline (ablation) | baseline INR · Chest (3D cone-beam, 10 views) | PSNR: 25.19 -> 28.74 | Improved |
| add TPSE and TPVS to baseline (ablation) | baseline INR · Chest (3D cone-beam, 30 views) | PSNR: 28.49 -> 38.50 | Improved |
| use FDK prior with TPSE instead of no structural encoding (ablation) | TPG-INR · Chest (3D cone-beam, 20 views) | PSNR: 32.76 -> 33.45 | Improved |
| use SART-TV prior with TPSE instead of no structural encoding (ablation) | TPG-INR · Chest (3D cone-beam, 20 views) | PSNR: 32.76 -> 34.48 | Improved |
| use TPE prior instead of SART-TV prior (ablation) | TPG-INR · Chest (3D cone-beam, 20 views) | PSNR: 34.48 -> 35.55 | Improved |
| use TPE prior instead of FDK prior (ablation) | TPG-INR · Chest (3D cone-beam, 20 views) | PSNR: 33.45 -> 35.55 | Improved |
| use TPE prior estimate versus FDK prior estimate directly (ablation) | target prior estimate · Chest (3D cone-beam, 20 views) | PSNR: 20.99 -> 28.88 | Improved |
| use TPVS sampling instead of uniform sampling across voxel counts (ablation) | TPG-INR · Chest (3D cone-beam, 10/20/30 views) | PSNR | Improved |
| increase sampled voxels per ray (ablation) | TPVS · Chest (3D cone-beam) | convergence time | Mixed |
Closest papers by meaning
- Structure-Aware Sparse-View X-ray 3D Reconstruction (CVPR 2024 · similarity 0.87)
- DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction (NeurIPS 2024 · similarity 0.86)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (AAAI 2024 · similarity 0.86)
- Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction (AAAI 2025 · similarity 0.86)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.86)
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.86)
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.
