mlsanityData to 14 Oct 2026

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

arXiv 2201.05989 ↗First posted 16 Jan 2022cs.CV cs.GR cs.LGcited by 3,723

Not on the map. Why?

Cited by 268 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of 1920!×!1080.

Key facts. Cited by 3,723 papers in the map (data through 14 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 16 Jan 2022.

Builds on

31 of 55 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  4. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  5. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  8. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  9. 2017Mixed Precision Trainingcited by 1,156
  10. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
19 more
  1. 2020Convolutional Occupancy Networkscited by 761
  2. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  3. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  4. 2017Convolutional Sequence to Sequence Learningcited by 552
  5. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 533
  6. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  7. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  8. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  9. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  10. 2021NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Imagescited by 336
  11. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  12. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  13. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
  14. 2018Neural Importance Samplingcited by 155
  15. 2021Modulated Periodic Activations for Generalizable Local Functional Representationscited by 140
  16. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  17. 2021Real-time Neural Radiance Caching for Path Tracingcited by 91
  18. 2020Neural Control Variatescited by 34
  19. 2021Neural Radiositycited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 264; 2023: 847; 2024: 1197; 2025: 869; 2026: 546.

3,723 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  3. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  4. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  5. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  7. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  8. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  9. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  10. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  11. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  12. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
38 more
  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  2. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  3. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  4. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
  5. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  6. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  8. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  9. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  10. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  11. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  12. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  13. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  14. 2023LERF: Language Embedded Radiance Fieldscited by 543
  15. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  16. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  17. 2023Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splattingcited by 476
  18. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  19. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  20. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  21. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  22. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  23. 2023Gaussian Splatting SLAMcited by 415
  24. 2023LangSplat: 3D Language Gaussian Splattingcited by 415
  25. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 397
  26. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  27. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 377
  28. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
  29. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 371
  30. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
  31. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  32. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 360
  33. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  34. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
  35. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  36. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
  37. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 343
  38. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341

50 most cited of 3,723 All 3,723 (JSON)