Research map / 3D vision / NeRF and radiance fields
NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
Read the paperCheck 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 holistic geometry priors and NeRFVS regularization to NeRF | NeRF · ScanNet extrapolation, Scene0050_00 | PSNR: 21.625 -> 24.261 | Helped |
| Add holistic geometry priors and NeRFVS regularization to NeRF | NeRF · Barbershop extrapolation | PSNR: 24.367 -> 26.946 | Helped |
| Add robust depth loss instead of L2 depth loss (ablation) | NeRFVS on ScanNet · ScanNet extrapolation | PSNR: 23.187 -> 23.714 | Helped |
| Add weight and color variance losses (ablation) | NeRFVS on ScanNet · ScanNet extrapolation | PSNR: 23.435 -> 23.714 | Helped |
| Add view coverage-based adjustment to depth and variance regularization (ablation) | NeRFVS on ScanNet · ScanNet extrapolation | PSNR: 23.172 -> 23.714 | Helped |
| Use the geometry scaffold depth rather than Colmap MVS depth | DS-NeRF · ScanNet extrapolation | PSNR: 20.906 -> 21.385 | Helped |
| Use Colmap MVS as the geometry scaffold | NeRFVS · ScanNet extrapolation | PSNR: 23.714 -> 22.771 | Hurt |
Closest papers by meaning
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.92)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.91)
- Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes (CVPR 2024 · similarity 0.90)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.89)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (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.