Research map / 3D vision / NeRF and radiance fields
NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo
Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie Zhou
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 |
|---|---|---|---|
| add adapted depth priors to guide NeRF sampling (ablation) | NeRF · ScanNet scene0521 | Abs Rel: 0.302 -> 0.053 | Improved |
| add confidence-based filter (ablation) | NeRF + depth priors · ScanNet scene0521 | Abs Rel: 0.053 -> 0.051 | Improved |
| add confidence filter to full method (ablation) | Ours · ScanNet (8 scenes) | Abs Rel: 0.0635 -> 0.0614 | Improved |
| add NeRF optimization over the depth priors (ablation) | depth priors · ScanNet scene0521 | Abs Rel: 0.067 -> 0.053 | Improved |
| add adaptive sampling range (ablation) | guided optimization · ScanNet scene0521 | Abs Rel: 0.065 -> 0.056 | Improved |
| add bounds alpha_l and alpha_h (ablation) | guided optimization · ScanNet scene0521 | Abs Rel: 0.056 -> 0.051 | Improved |
| apply CVD optimization on adapted priors | adapted depth priors · ScanNet (8 scenes) | Abs Rel: 0.0844 -> 0.0886 | Hurt |
| apply guided NeRF optimization on adapted priors | adapted depth priors · ScanNet (8 scenes) | Abs Rel: 0.0844 -> 0.0635 | Improved |
| finetune monocular depth net on scene COLMAP reconstruction | Mannequin · ScanNet (8 scenes) | Abs Rel: 0.1554 -> 0.0844 | Improved |
| use guided optimization instead of vanilla NeRF | NeRF · ScanNet seen views | PSNR: 28.62 -> 31.55 | Improved |
| use guided optimization instead of vanilla NeRF | NeRF · ScanNet novel views | PSNR: 15.76 -> 18.07 | Improved |
| set K=4 instead of K=2 (ablation) | Ours · ScanNet scene0521 | Abs Rel: 0.055 -> 0.051 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DELTAS — DELTAS: Depth Estimation by Learning Triangulation And densification of Sparse points (ECCV 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Depth-Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo (TPAMI 2023 · similarity 0.99)
- Dense Depth Priors for Neural Radiance Fields From Sparse Input Views (CVPR 2022 · similarity 0.94)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (CVPR 2025 · similarity 0.92)
- Global and Hierarchical Geometry Consistency Priors for Few-shot NeRFs in Indoor Scenes (CVPR 2024 · similarity 0.92)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · 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.
