Research map / 3D vision / Gaussian splatting
GH-NAF: Grid-Adaptive Hash-Level-Attended Neural Attenuation Fields for Discrepancy-Aware CBCT
Seong Je Oh, Ju Hwan Lee, Chae Yeon Lim, Donghwan Lee, Myung Jin Chung, Kyungsu Kim
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 uncertainty-weighted projection loss with discrepancy rendering instead of plain MSE (ablation) | GH-NAF · Synthetic CT | PSNR: 34.06 -> 39.82 | Improved |
| add hash-level attention alignment loss Lattn (ablation) | GH-NAF · Synthetic CT | PSNR: 39.59 -> 39.82 | Improved |
| add occlusion regularization Locc (ablation) | GH-NAF · Synthetic CT | PSNR: 39.75 -> 39.82 | Improved |
| add density regularization Lden together with Locc (ablation) | GH-NAF · Synthetic CT | PSNR: 39.28 -> 39.82 | Improved |
| use GH-NAF instead of NeRF baselines under strong projection discrepancy | NAF/SAX · Chest phantom | MANIQA: SAX 0.353 -> 0.392 (150 views) | Improved |
| use GH-NAF instead of Gaussian methods on discrepancy-free data | R2-Gaussian · Synthetic CT (15 views) | PSNR: 34.34 -> 33.56 | Hurt |
| use GH-NAF instead of Gaussian methods on discrepancy-free data | R2-Gaussian · Synthetic CT (15 views) | SSIM: 0.895 -> 0.934 | Improved |
| use GH-NAF instead of R2-Gaussian on low-discrepancy FIPS | R2-Gaussian · FIPS (Walnut/Seashell/Pine) | PSNR: Walnut 25v 45.24 -> 46.54; Seashell 25v 41.90 -> 39.91 | Mixed |
Closest papers by meaning
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.83)
- Plug-and-Play Tri-Branch Invertible Block for Image Rescaling (AAAI 2025 · similarity 0.83)
- Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification (AAAI 2025 · similarity 0.83)
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.82)
- A Unified Model for Compressed Sensing MRI Across Undersampling Patterns (CVPR 2025 · similarity 0.82)
- Spatiotemporal-Aware Neural Fields for Dynamic CT Reconstruction (AAAI 2025 · similarity 0.82)
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.
