mlsanityData to 7 Oct 2026

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

arXiv 2103.13744 ↗First posted 25 Mar 2021cs.CVcited by 672

Not on the map. Why?

Abstract (arXiv)

NeRF synthesizes novel views of a scene with unprecedented quality by fitting a neural radiance field to RGB images. However, NeRF requires querying a deep Multi-Layer Perceptron (MLP) millions of times, leading to slow rendering times, even on modern GPUs. In this paper, we demonstrate that real-time rendering is possible by utilizing thousands of tiny MLPs instead of one single large MLP. In our setting, each individual MLP only needs to represent parts of the scene, thus smaller and faster-to-evaluate MLPs can be used. By combining this divide-and-conquer strategy with further optimizations, rendering is accelerated by three orders of magnitude compared to the original NeRF model without incurring high storage costs. Further, using teacher-student distillation for training, we show that this speed-up can be achieved without sacrificing visual quality.

Key facts. Cited by 672 papers in the map (data through 7 Oct 2026). Builds on 47 of its 78 references that are in the map. First posted on arXiv 25 Mar 2021.

Builds on

47 of 78 references.

References · 47

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  8. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
35 more
  1. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  2. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  3. 2020Convolutional Occupancy Networkscited by 760
  4. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  5. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  6. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  7. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  8. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  9. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  10. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  11. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  12. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 493
  13. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  14. 2020Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstructioncited by 465
  15. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  16. 2020Space-time Neural Irradiance Fields for Free-Viewpoint Videocited by 414
  17. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  18. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 381
  19. 2019Neural Point-Based Graphicscited by 326
  20. 2020Neural Scene Graphs for Dynamic Scenescited by 298
  21. 2020Neural Radiance Flow for 4D View Synthesis and Video Processingcited by 270
  22. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  23. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  24. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 240
  25. 2020Free View Synthesiscited by 231
  26. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  27. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  28. 2020Stable View Synthesiscited by 165
  29. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  30. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  31. 2020Object-Centric Neural Scene Renderingcited by 90
  32. 2020Learning Compositional Radiance Fields of Dynamic Human Headscited by 78
  33. 2020Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illuminationcited by 62
  34. 2020Portrait Neural Radiance Fields from a Single Imagecited by 61
  35. 2020Learning Implicit Surface Light Fieldscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 47; 2022: 142; 2023: 199; 2024: 152; 2025: 96; 2026: 36.

672 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  3. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  4. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  5. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  6. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  8. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  9. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 753
  10. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  11. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  12. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
38 more
  1. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  2. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 596
  3. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  4. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  7. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  8. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  9. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  10. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  11. 2021Advances in Neural Renderingcited by 365
  12. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  13. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  14. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  15. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  16. 2021Text2Mesh: Text-Driven Neural Stylization for Meshescited by 332
  17. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  18. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  19. 2023UniSim: A Neural Closed-Loop Sensor Simulatorcited by 294
  20. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  21. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  22. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  23. 2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
  24. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  25. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  26. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  27. 2024A Survey on 3D Gaussian Splattingcited by 221
  28. 2023WIRE: Wavelet Implicit Neural Representationscited by 220
  29. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  30. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  31. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  32. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  33. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  34. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  35. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  36. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  37. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
  38. 2021Shape As Points: A Differentiable Poisson Solvercited by 186

50 most cited of 672 All 672 (JSON)