Research map / 3D vision / NeRF and radiance fields
Block-NeRF: Scalable Large Scene Neural View Synthesis
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 |
|---|---|---|---|
| Split the scene into more blocks while keeping per-block weights fixed (ablation) | Block-NeRF · Mission Bay | PSNR: 23.83 -> 27.40 | Helped |
| Split the scene into more blocks while holding total weights constant (ablation) | Block-NeRF · Mission Bay | PSNR: 24.90 -> 25.98 | Helped |
| Add appearance embeddings (ablation) | Block-NeRF · Alamo Square, single intersection | PSNR: 20.13 -> 23.60 | Helped |
| Add exposure input (ablation) | Block-NeRF · Alamo Square, single intersection | PSNR: 23.55 -> 23.60 | Helped |
| Add pose optimization (ablation) | Block-NeRF · Alamo Square, single intersection | PSNR: 23.05 -> 23.60 | Helped |
| Use 2D inverse distance weighting instead of nearest-block interpolation (ablation) | Block-NeRF compositing · Mission Bay | PSNR: 26.40 -> 26.59 | Helped |
| Use visibility-based interpolation (ablation) | Block-NeRF compositing · Mission Bay | PSNR: 26.59 -> 27.39 | Helped |
| Use visibility-based interpolation (ablation) | Block-NeRF compositing · Mission Bay flythroughs | temporal consistency | Hurt |
| Increase block overlap (ablation) | Block-NeRF · Mission Bay, 8 blocks | PSNR: 26.77 -> 26.59 | Hurt |
| Use 3D inverse distance weighting (ablation) | Block-NeRF compositing · Mission Bay | temporal consistency | Hurt |
| Add appearance embeddings (ablation) | Block-NeRF · Alamo Square, single intersection | LPIPS: 0.458 -> 0.417 | Helped |
| Add pose optimization (ablation) | Block-NeRF · Alamo Square, single intersection | LPIPS: 0.442 -> 0.417 | Helped |
Closest papers by meaning
- Grid-Guided Neural Radiance Fields for Large Urban Scenes (CVPR 2023 · similarity 0.92)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.91)
- Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields (ICLR 2023 · similarity 0.91)
- D-NeRF: Neural Radiance Fields for Dynamic Scenes (CVPR 2021 · 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)
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.