Research map / 3D vision / NeRF and radiance fields
Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields
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 |
|---|---|---|---|
| Use Mip-NeRF 360 instead of mip-NeRF | Mip-NeRF 360 · Mip-NeRF 360 dataset | PSNR: 24.04 -> 27.69 | Helped |
| Remove proposal loss (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 20.49 | Hurt |
| Remove distortion loss (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 24.41 | No clear effect |
| Replace distortion loss with Gaussian noise injection (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 24.00 | Hurt |
| Remove proposal MLP (ablation) | Mip-NeRF 360 · bicycle | training time (hrs): 7.09 -> 18.89 | Hurt |
| Remove proposal MLP and apply reconstruction loss at all coarse scales (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 23.45 | Hurt |
| Reduce NeRF MLP width from 1024 to 256 hidden units (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 22.80 | Hurt |
| Replace integrated positional encoding with NeRF positional encoding (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 23.87 | Hurt |
| Remove contraction and use additional positional encoding frequencies (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 23.77 | Hurt |
| Replace contraction and ray spacing with DONeRF's parameterization (ablation) | Mip-NeRF 360 · bicycle | PSNR: 24.37 -> 23.99 | Hurt |
| Remove off-axis positional encoding features (ablation) | Mip-NeRF 360 · bicycle | SSIM: 0.687 -> 0.664 | Hurt |
| Remove proposal-weight annealing (ablation) | Mip-NeRF 360 · bicycle | SSIM: 0.687 -> 0.679 | Hurt |
Closest papers by meaning
- PyNeRF: Pyramidal Neural Radiance Fields (NeurIPS 2023 · similarity 0.93)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.91)
- Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis? (CVPR 2024 · similarity 0.91)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.91)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.90)
- NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning (AAAI 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.