Research map / 3D vision / NeRF and radiance fields
Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields
Wenbo Hu, Yuling Wang, Lin Ma, Bangbang Yang, Lin Gao, Xiao Liu, Yuewen Ma
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 Tri-Mip (mipmap) encoding instead of plain 2D feature maps (ablation) | Tri-MipRF · Multi-scale Blender | PSNR (Avg.): 31.48 -> 35.06 | Improved |
| add area loss (scale pixel loss by footprint) (ablation) | NeRF · Multi-scale Blender | PSNR (Avg.): 27.66 -> 31.23 | Improved |
| add 5x super-sampling to hash encoding | Instant-ngp · Multi-scale Blender | PSNR (Avg.): 31.20 -> 31.94 | Improved |
| add 5x super-sampling to hash encoding | Instant-ngp · Multi-scale Blender | training time: 5 min -> 10 min | Hurt |
| use mipmap query (Tri-Mip) vs plain feature maps for reconstruction time (ablation) | Tri-MipRF · Multi-scale Blender | training time: 4.5 min -> 5 min | Mixed |
| use Tri-MipRF instead of Instant-ngp on constant-distance captures | Instant-ngp · Single-scale Blender | PSNR: 33.18 -> 33.65 | Improved |
| use Tri-Mip encoding (three base-level 2D maps) instead of hash table | Instant-ngp · Single-scale Blender | model size: 64.1 MB -> 48.2 MB | Improved |
| use Tri-MipRF instead of MipNeRF (explicit hybrid vs implicit) | MipNeRF · Multi-scale Blender | PSNR (Avg.): 34.51 -> 35.06 | Improved |
Later papers that compared with this method
3 later accepted papers report Tri-MipRF as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting (AAAI 2026 · better on 2 of 2 shared results)
- Spatial Annealing for Efficient Few-shot Neural Rendering (AAAI 2025 · better on 1 of 1 shared result)
- URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fields (ECCV 2024 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MipNeRF — Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 2021) · better on 4 of 4 shared results
- Plenoxels — Plenoxels: Radiance Fields Without Neural Networks (CVPR 2022) · better on 1 of 1 shared result
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
- Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields (NeurIPS 2023 · similarity 0.92)
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields (ICCV 2021 · similarity 0.90)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · similarity 0.88)
- Is Vanilla MLP in Neural Radiance Field Enough for Few-shot View Synthesis? (CVPR 2024 · similarity 0.88)
- TeTriRF: Temporal Tri-Plane Radiance Fields for Efficient Free-Viewpoint Video (CVPR 2024 · similarity 0.88)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.87)
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.
