Research map / 3D vision / Depth and stereo
3D Image Reconstruction from X-Ray Measurements with Overlap
Maria Klodt, Raphael Hauser
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 |
|---|---|---|---|
| model overlapping rays with the nonlinear exponential-sum constraint instead of discarding overlapping measurements | X-ray reconstruction with L1/TV prior · Simulated cube, 20x20x20 voxels | relative reconstruction error d(x) | Improved |
| model overlapping rays with the nonlinear constraint instead of discarding overlapping measurements | X-ray reconstruction · Real data letters and polecat (512x512x20) | distance to sequential reconstruction | Improved |
| increase average overlap of simultaneously emitting sources | overlap-aware reconstruction · Simulated and real data | reconstruction error | Hurt |
| handle overlap with backtracking line search and exponentials instead of linear constraints | reconstruction algorithm · computation time | run time: approximately 5 times slower | Hurt |
Closest papers by meaning
- X-Field: A Physically Informed Representation for 3D X-ray Reconstruction (NeurIPS 2025 · similarity 0.85)
- Structure-Aware Sparse-View X-ray 3D Reconstruction (CVPR 2024 · similarity 0.83)
- Revisiting Pose Sensitivity in Splat-based Computed Tomography under Sparse-view Reconstruction (CVPR 2026 · similarity 0.83)
- X-Ray: A Sequential 3D Representation For Generation (NeurIPS 2024 · similarity 0.81)
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction (NeurIPS 2024 · similarity 0.81)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.79)
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.
