Research map / 3D vision / NeRF and radiance fields
Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, Pratul P. Srinivasan
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 integrated positional encoding (cone-casting features) (ablation) | Mip-NeRF · Multiscale Blender | average error: 0.0186 -> 0.0114 | Improved |
| add integrated positional encoding (ablation) | Mip-NeRF · Blender (single-scale) | average error: 0.0173 -> 0.0161 | Improved |
| add pixel-area loss scaling (ablation) | Mip-NeRF · Multiscale Blender | average error: 0.0139 -> 0.0114 | Improved |
| add pixel-area loss scaling | NeRF · Multiscale Blender | average error: 0.0288 -> 0.0305 | Mixed |
| use centered pixels | NeRF + Area Loss · Multiscale Blender | average error: 0.0305 -> 0.0191 | Improved |
| use centered pixels | NeRF · Blender (single-scale) | average error: 0.0194 -> 0.0178 | Improved |
| add misc. stability changes (ablation) | Mip-NeRF · Multiscale Blender | average error: 0.0114 -> 0.0114 | No clear effect |
| replace two MLPs with a single multiscale MLP (ablation) | Mip-NeRF · Multiscale Blender | training time (hours): 3.40 -> 2.84 | Improved |
| replace two MLPs with a single multiscale MLP (ablation) | Mip-NeRF · Blender (single-scale) | PSNR: 32.71 -> 33.09 | Improved |
| add supersampling | Mip-NeRF · Multiscale Blender | mean PSNR: 34.46 -> 35.03 | Improved |
| use mip-NeRF instead of supersampled NeRF | NeRF · Multiscale Blender | render time (sec./MP): 55.52 -> 2.48 | Improved |
| use mip-NeRF cone tracing instead of NeRF | NeRF · Multiscale Blender | average error: 60% | Improved |
Later papers that compared with this method
38 later accepted papers report Mip-NeRF as a baseline in their results tables; 28 of them report a better number on most of the results they share with it.
- RefracGS: Novel View Synthesis Through Refractive Water Surfaces with 3D Gaussian Ray Tracing (ECCV 2026 · better on 3 of 3 shared results)
- MS-NeRF: Multi-Space Neural Radiance Fields (TPAMI 2025 · better on 2 of 2 shared results)
- HyRF: Hybrid Radiance Fields for Memory-efficient and High-quality Novel View Synthesis (NeurIPS 2025 · better on 0 of 1 shared result)
- AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction (ICLR 2025 · better on 0 of 1 shared result)
- HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity (ICCV 2025 · better on 1 of 1 shared result)
- HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Driving (TPAMI 2025 · better on 1 of 1 shared result)
- Coordinate-Aware Modulation for Neural Fields (ICLR 2024 · better on 6 of 6 shared results)
- SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field (AAAI 2024 · better on 4 of 5 shared results)
30 more not listed.
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-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields (CVPR 2022 · similarity 0.94)
- Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields (ICCV 2023 · similarity 0.93)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.92)
- 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 0.90)
- Ced-NeRF: A Compact and Efficient Method for Dynamic Neural Radiance Fields (AAAI 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.
