Research map / 3D vision / NeRF and radiance fields
Ray Priors Through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 random ray casting (RRC) (ablation) | NeRF · MobileObject | PSNR: 24.05 -> 27.55 | Helped |
| Add ray atlas (RA) (ablation) | NeRF · MobileObject | PSNR: 24.05 -> 25.29 | Helped |
| Add both RRC and RA (ablation) | NeRF · MobileObject | PSNR: 24.05 -> 28.90 | Helped |
| Set RRC elevation threshold η to 10° rather than 30° (ablation) | RapNeRF · Skull | PSNR: 27.86 -> 26.89 | Hurt |
| Set RRC elevation threshold η to 20° rather than 30° (ablation) | RapNeRF · Skull | PSNR: 27.86 -> 27.32 | Hurt |
| Set RRC elevation threshold η to 40° rather than 30° (ablation) | RapNeRF · Skull | PSNR: 27.86 -> 26.72 | Hurt |
| Set RRC elevation threshold η to 50° rather than 30° (ablation) | RapNeRF · Skull | PSNR: 27.86 -> 27.38 | Hurt |
| Set RRC elevation threshold η to 60° rather than 30° (ablation) | RapNeRF · Skull | PSNR: 27.86 -> 27.29 | Hurt |
| Use RapNeRF for novel-view extrapolation instead of the strongest listed baseline | NeRF and its compared variants · Synthetic-NeRF* | PSNR: 26.37 -> 27.63 | Helped |
| Use RapNeRF for novel-view extrapolation instead of the strongest listed baseline | NeRF and its compared variants · MobileObject | PSNR: 26.69 -> 28.90 | Helped |
Closest papers by meaning
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs (CVPR 2022 · similarity 0.93)
- ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models (CVPR 2024 · similarity 0.91)
- Few-Shot Neural Radiance Fields under Unconstrained Illumination (AAAI 2024 · similarity 0.91)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.90)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (CVPR 2025 · similarity 0.89)
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.