Research map / 3D vision / NeRF and radiance fields
AdaNeRF: Adaptive Sampling for Real-Time Rendering of Neural Radiance Fields
Andreas Kurz, Thomas Neff, Zhaoyang Lv, Michael Zollhöfer, Markus Steinberger
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 dense training phase (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 27.69 -> 28.25 | Improved |
| add dense training phase (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=4) | PSNR: 29.23 -> 29.33 | Improved |
| add sparsification blending (gradual dense-to-sparse) (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 27.33 -> 28.25 | Improved |
| add sparsification blending (gradual dense-to-sparse) (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=4) | PSNR: 28.44 -> 29.33 | Improved |
| add density multiplication in ray accumulation (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 24.75 -> 28.25 | Improved |
| add shading-density-supervised sparsity loss combined with MSE (instead of only L1 shading supervision) (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 24.72 -> 28.25 | Improved |
| add shading density supervision L1 term (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 27.82 -> 28.25 | Improved |
| add shading density supervision L1 term (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=4) | PSNR: 28.86 -> 29.33 | Improved |
| add sparse training phase (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=2) | PSNR: 21.38 -> 28.25 | Improved |
| add sparse training phase (ablation) | AdaNeRF · DONeRF Pavillon (Nmax=4) | PSNR: 28.39 -> 29.33 | Improved |
| use adaptive sampling (tau=0.35, 6.16 samples) instead of fixed N=8 (ablation) | AdaNeRF · DONeRF Pavillon | PSNR: 30.40 -> 30.64 | Improved |
| use adaptive sampling (tau=0.3, 7.76 samples) instead of fixed N=16 (ablation) | AdaNeRF · DONeRF Pavillon | PSNR: 30.89 -> 31.07 | Improved |
Later papers that compared with this method
1 later accepted paper reports AdaNeRF-11 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Efficient View Synthesis with Neural Radiance Distribution Field (ICCV 2023 · better on 2 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- Plenoxels — Plenoxels: Radiance Fields Without Neural Networks (CVPR 2022) · better on 1 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
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs (CVPR 2022 · similarity 0.91)
- Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction (CVPR 2025 · similarity 0.90)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.90)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (AAAI 2024 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.89)
- Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation (ICLR 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.
