Research map / 3D vision / NeRF and radiance fields
BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-Scale Scene Rendering
Yuanbo Xiangli, Linning Xu, Xingang Pan, Nanxuan Zhao, Anyi Rao, Christian Theobalt, Bo Dai, Dahua Lin
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 inclusive multi-level supervision (all earlier scales per head) (ablation) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 22.773 -> 23.481 | Improved |
| add progressive data feeding schedule (ablation) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 22.340 -> 23.481 | Improved |
| add progressive model growing with new blocks (ablation) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 22.139 -> 23.481 | Improved |
| add skip layer in additive blocks (ablation) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 23.159 -> 23.481 | Improved |
| add residual connection between growing blocks (ablation) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 23.139 -> 23.481 | Improved |
| add inclusive multi-level supervision (ablation) | BungeeNeRF · Transamerica (San Francisco) | average PSNR: 22.789 -> 23.606 | Improved |
| add progressive data feeding schedule (ablation) | BungeeNeRF · Transamerica (San Francisco) | average PSNR: 23.015 -> 23.606 | Improved |
| add skip layer at Stage IV (ablation) | BungeeNeRF · Transamerica (San Francisco), Stage IV | PSNR: 22.151 -> 22.942 | Improved |
| use BungeeNeRF instead of Mip-NeRF-full (trained to convergence) | BungeeNeRF · 56 Leonard (New York) | average PSNR: 22.312 -> 24.513 | Improved |
| use BungeeNeRF instead of Mip-NeRF-full (trained to convergence) | BungeeNeRF · Transamerica (San Francisco) | average PSNR: 22.828 -> 24.415 | Improved |
| add windowed positional encoding to NeRF | NeRF · 56 Leonard (New York) | average PSNR: 21.702 -> 21.672 | No clear effect |
| enlarge Mip-NeRF from small (D=8) to large (D=10) | Mip-NeRF · 56 Leonard (New York) | average PSNR: 21.975 -> 22.227 | Improved |
Closest papers by meaning
- PyNeRF: Pyramidal Neural Radiance Fields (NeurIPS 2023 · similarity 0.91)
- Grid-Guided Neural Radiance Fields for Large Urban Scenes (CVPR 2023 · similarity 0.91)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 2024 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.90)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.90)
- FrugalNeRF: Fast Convergence for Extreme Few-shot Novel View Synthesis without Learned Priors (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.
