Research map / 3D vision / NeRF and radiance fields
Dense Depth Priors for Neural Radiance Fields From Sparse Input Views
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 |
|---|---|---|---|
| use dense depth priors with uncertainty instead of NeRF alone | NeRF · ScanNet | PSNR: 19.03 -> 20.96 | Helped |
| use dense depth priors with uncertainty instead of NeRF alone | NeRF · ScanNet | Depth RMSE: 1.163 -> 0.236 | Helped |
| use dense depth priors with uncertainty instead of DS-NeRF | DS-NeRF · ScanNet | PSNR: 20.85 -> 20.96 | Helped |
| use dense depth priors with uncertainty instead of DS-NeRF | DS-NeRF · ScanNet | Depth RMSE: 0.447 -> 0.236 | Helped |
| use dense depth priors with uncertainty instead of NeRF | NeRF · Matterport3D | PSNR: 15.24 -> 18.33 | Helped |
| use dense depth priors with uncertainty instead of NeRF | NeRF · Matterport3D | Depth RMSE: 1.362 -> 0.114 | Helped |
| add depth completion to sparse depth input (ablation) | Ours · ScanNet | Depth RMSE: 0.526 -> 0.236 | Helped |
| add depth completion to sparse depth input (ablation) | Ours · Matterport3D | PSNR: 16.90 -> 18.33 | Helped |
| add depth completion to sparse depth input (ablation) | Ours · Matterport3D | Depth RMSE: 0.427 -> 0.114 | Helped |
| include uncertainty in the optimization (ablation) | Ours · ScanNet | Depth RMSE: 0.279 -> 0.236 | Helped |
| include uncertainty in the optimization (ablation) | Ours · Matterport3D | PSNR: 17.95 -> 18.33 | Helped |
| use GNLL rather than MSE for the depth loss (ablation) | Ours · ScanNet | Depth RMSE: 0.275 -> 0.236 | Helped |
Closest papers by meaning
- Depth-Supervised NeRF: Fewer Views and Faster Training for Free (CVPR 2022 · similarity 0.93)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.92)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.91)
- AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization (AAAI 2024 · similarity 0.90)
- ZeroRF: Fast Sparse View 360deg Reconstruction with Zero Pretraining (CVPR 2024 · similarity 0.90)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.90)
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.