mlsanityData to 7 Oct 2026

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

arXiv 2103.13415 ↗First posted 24 Mar 2021cs.CV cs.GRcited by 1,957

Not on the map. Why?

Cited by 113 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The rendering procedure used by neural radiance fields (NeRF) samples a scene with a single ray per pixel and may therefore produce renderings that are excessively blurred or aliased when training or testing images observe scene content at different resolutions. The straightforward solution of supersampling by rendering with multiple rays per pixel is impractical for NeRF, because rendering each ray requires querying a multilayer perceptron hundreds of times. Our solution, which we call "mip-NeRF" (a la "mipmap"), extends NeRF to represent the scene at a continuously-valued scale. By efficiently rendering anti-aliased conical frustums instead of rays, mip-NeRF reduces objectionable aliasing artifacts and significantly improves NeRF's ability to represent fine details, while also being 7% faster than NeRF and half the size. Compared to NeRF, mip-NeRF reduces average error rates by 17% on the dataset presented with NeRF and by 60% on a challenging multiscale variant of that dataset that we present. Mip-NeRF is also able to match the accuracy of a brute-force supersampled NeRF on our multiscale dataset while being 22x faster.

Key facts. Cited by 1,957 papers in the map (data through 7 Oct 2026). Builds on 23 of its 53 references that are in the map. First posted on arXiv 24 Mar 2021.

Builds on

23 of 53 references.

References · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  11. 2017In-Datacenter Performance Analysis of a Tensor Processing Unitcited by 610
  12. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
11 more
  1. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  2. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  3. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  4. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  5. 2019Making Convolutional Networks Shift-Invariant Againcited by 390
  6. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  7. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  8. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  9. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  10. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  11. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 45; 2022: 187; 2023: 478; 2024: 608; 2025: 412; 2026: 227.

1,957 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  4. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  7. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  8. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  9. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  10. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  11. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  12. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
38 more
  1. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 742
  2. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  3. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  4. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  5. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  6. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  7. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  8. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  9. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  10. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  11. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  12. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  13. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  14. 2021Neural Fields in Visual Computing and Beyondcited by 539
  15. 2023LERF: Language Embedded Radiance Fieldscited by 538
  16. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  17. 2021Zero-Shot Text-Guided Object Generation with Dream Fieldscited by 513
  18. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  19. 2022HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Videocited by 483
  20. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 470
  21. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  22. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  23. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  24. 2021Advances in Neural Renderingcited by 365
  25. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  26. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  27. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  28. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  29. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  30. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  31. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  32. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  33. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  34. 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
  35. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  36. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  37. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  38. 2023Text-to-3D using Gaussian Splattingcited by 299

50 most cited of 1,957 All 1,957 (JSON)