Research map / 3D vision / Depth and stereo
Neuromorphic X-ray Computed Tomography
Hongjian Wang, Goran Lovric, Benjamín Béjar
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 |
|---|---|---|---|
| use neuromorphic event supervision (ENAF) instead of frame-only NAF | NAF · Chest CT (5 views, synthetic) | PSNR (dB): 17.75 -> 29.79 | Improved |
| use ENAF instead of SAX-NeRF | SAX-NeRF · Chest CT (5 views, synthetic) | PSNR (dB): 20.52 -> 29.79 | Improved |
| add events at 25 views | NAF · Jaw CT (25 views, synthetic) | PSNR (dB): 30.37 -> 34.66 | Improved |
| add events when 50 views are available | SAX-NeRF · Abdomen/Foot/Jaw CT (50 views) | PSNR (dB): Foot 32.25 -> 32.45; Abdomen 34.95 -> 35.11 | Mixed |
| add events at 50 views on Chest | SAX-NeRF · Chest CT (50 views, synthetic) | PSNR (dB): 34.26 -> 34.57 | Improved |
| add timestamp jitter up to 10 ms to events (ablation) | ENAF · Chest CT (5 views, noisy events) | PSNR (dB): 29.79 -> 29.49 | No clear effect |
| add spurious events (50% of original count) (ablation) | ENAF · Chest CT (5 views, noisy events) | PSNR (dB): 29.79 -> 29.62 | No clear effect |
| use events with sparse frames vs events only (ablation) | ENAF · Real-world lattice (qualitative) | visual completeness | Improved |
| use ENAF instead of NAF on training efficiency | NAF · Chest CT (5 views, synthetic) | PSNR at ~5 min training: <18 -> ~30 dB | Improved |
Closest papers by meaning
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.86)
- Structure-Aware Sparse-View X-ray 3D Reconstruction (CVPR 2024 · similarity 0.85)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.84)
- Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction (AAAI 2025 · similarity 0.84)
- QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction (CVPR 2024 · similarity 0.84)
- Spatiotemporal-Aware Neural Fields for Dynamic CT Reconstruction (AAAI 2025 · similarity 0.84)
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.
