Research map / 3D vision / NeRF and radiance fields
RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields
Doriand Petit, Steve Bourgeois, Dumitru Pavel, Vincent Gay-Bellile, Florian Chabot, Loïc Barthe
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 RING-NeRF architecture (summed residual multi-scale grids) over Nerfacto concatenated grids (ablation) | Nerfacto · Mip-NeRF 360 (mono-scale, full res) | PSNR: 27.09 -> 27.65 | Improved |
| add distance-aware forward mapping (cone casting LOD selection) (ablation) | RING-NeRF · Mip-NeRF 360 (mono-scale, full res) | PSNR: 27.65 -> 28.26 | Improved |
| add continuous coarse-to-fine optimization on stable NVS setup (ablation) | RING-NeRF · Mip-NeRF 360 (mono-scale, full res) | PSNR: 28.26 -> 28.09 | No clear effect |
| add continuous coarse-to-fine instead of discrete (ablation) | RING-NeRF · DTU few-view (3 images) | PSNR: 15.79 -> 16.18 | Improved |
| add FreeNeRF density loss on few views (ablation) | RING-NeRF · DTU few-view (3 images) | PSNR: 10.56 -> 14.58 | Improved |
| add coarse-to-fine with density loss on few views (ablation) | RING-NeRF · DTU few-view (3 images) | PSNR: 14.58 -> 16.18 | Improved |
| RING-NeRF architecture instead of Nerfacto with progressive grids (Nerfacto+) | Nerfacto+ · DTU few-view (3 images) | PSNR: 13.61 -> 16.18 | Improved |
| use RING-NeRF for SDF reconstruction without scene-specific initialization | NeuS-facto · Replica SDF without initialization | Chamfer-L1 (cm): 17.61 -> 5.71 | Improved |
| RING-NeRF versus per-LOD or super-sampling anti-aliasing methods for training time | RING-NeRF · Mip-NeRF 360 | training time (hours): 1.10h -> 0.45h | Improved |
| RING-NeRF versus FreeNeRF on quality in few-view setting | RING-NeRF · DTU few-view (3 images) | PSNR: 19.92 -> 16.18 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 on most shared results.
- PyNeRF — PyNeRF: Pyramidal Neural Radiance Fields (NeurIPS 2023) · better on 3 of 3 shared results
- Zip-NeRF — Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023) · better on 3 of 3 shared results
- FreeNeRF — FreeNeRF: Improving Few-Shot Neural Rendering With Free Frequency Regularization (CVPR 2023) · better on 1 of 2 shared results
- Mip-NeRF — Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 2021) · 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
- HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork (NeurIPS 2023 · similarity 0.88)
- Is Attention All That NeRF Needs? (ICLR 2023 · similarity 0.88)
- Optimize the Unseen - Fast NeRF Cleanup with Free Space Prior (NeurIPS 2025 · similarity 0.86)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 2024 · similarity 0.86)
- PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields (CVPR 2025 · similarity 0.86)
- NeRF Director: Revisiting View Selection in Neural Volume Rendering (CVPR 2024 · similarity 0.86)
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.
