mlsanityData to 14 Oct 2026

NerfAcc: Efficient Sampling Accelerates NeRFs

arXiv 2305.04966 ↗First posted 8 May 2023cs.CVcited by 90

Not on the map. Why?

Abstract (arXiv)

Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering. Recent works have included alternative sampling approaches to help accelerate their methods, however, they are often not the focus of the work. In this paper, we investigate and compare multiple sampling approaches and demonstrate that improved sampling is generally applicable across NeRF variants under an unified concept of transmittance estimator. To facilitate future experiments, we develop NerfAcc, a Python toolbox that provides flexible APIs for incorporating advanced sampling methods into NeRF related methods. We demonstrate its flexibility by showing that it can reduce the training time of several recent NeRF methods by 1.5x to 20x with minimal modifications to the existing codebase. Additionally, highly customized NeRFs, such as Instant-NGP, can be implemented in native PyTorch using NerfAcc.

Key facts. Cited by 90 papers in the map (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

29 of 39 references.

References · 29

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  3. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  7. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  12. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
17 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  2. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
  3. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  4. 2023K-Planes: Explicit Radiance Fields in Space, Time, and Appearancecited by 746
  5. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  7. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  8. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  9. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  10. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  11. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 346
  12. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
  13. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  14. 2022TAVA: Template-free Animatable Volumetric Actorscited by 172
  15. 2022Variable Bitrate Neural Fieldscited by 117
  16. 2019Kaolin: A PyTorch Library for Accelerating 3D Deep Learning Researchcited by 98
  17. 2022Improved Direct Voxel Grid Optimization for Radiance Fields Reconstructioncited by 61

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 27; 2024: 31; 2025: 24; 2026: 8.

90 papers.

Sort:

By area:

  1. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  2. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 217
  3. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  4. 2023NeuRAD: Neural Rendering for Autonomous Drivingcited by 150
  5. 2023Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusioncited by 106
  6. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generationcited by 104
  7. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  8. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 58
  9. 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
  10. 2023Learning Disentangled Avatars with Hybrid 3D Representationscited by 44
  11. 2023DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelinescited by 36
  12. 2024HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splattingcited by 35
38 more
  1. 2024Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Renderingcited by 35
  2. 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Priorcited by 31
  3. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  4. 2025Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustmentcited by 27
  5. 2023Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Viewscited by 25
  6. 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priorscited by 25
  7. 2024UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstructioncited by 24
  8. 2024OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flowcited by 22
  9. 2024GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Viewscited by 22
  10. 2023IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracingcited by 20
  11. 2024MVGS: Multi-view Regulated Gaussian Splatting for Novel View Synthesiscited by 20
  12. 2024NeRF-XL: Scaling NeRFs with Multiple GPUscited by 19
  13. 2024SparseCraft: Few-Shot Neural Reconstruction through Stereopsis Guided Geometric Linearizationcited by 19
  14. 2023SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integrationcited by 18
  15. 2023Accelerating Neural Field Training via Soft Miningcited by 15
  16. 2024Lightplane: Highly-Scalable Components for Neural 3D Fieldscited by 13
  17. 2023FastSR-NeRF: Improving NeRF Efficiency on Consumer Devices with A Simple Super-Resolution Pipelinecited by 12
  18. 2024What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANscited by 12
  19. 2024Neural Radiance Field-based Visual Rendering: A Comprehensive Reviewcited by 12
  20. 2024SurgicalGaussian: Deformable 3D Gaussians for High-Fidelity Surgical Scene Reconstructioncited by 11
  21. 2024Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditionscited by 10
  22. 2023Volumetric Rendering with Baked Quadrature Fieldscited by 9
  23. 2024Evaluating Alternatives to SFM Point Cloud Initialization for Gaussian Splattingcited by 9
  24. 2023BAA-NGP: Bundle-Adjusting Accelerated Neural Graphics Primitivescited by 8
  25. 2023Neural Processing of Tri-Plane Hybrid Neural Fieldscited by 8
  26. 2026Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesiscited by 8
  27. 2024Flying with Photons: Rendering Novel Views of Propagating Lightcited by 7
  28. 2024SafeguardGS: 3D Gaussian Primitive Pruning While Avoiding Catastrophic Scene Destructioncited by 7
  29. 2025GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Modelscited by 7
  30. 2024CorrespondentDream: Enhancing 3D Fidelity of Text-to-3D using Cross-View Correspondencescited by 6
  31. 2024LLaNA: Large Language and NeRF Assistantcited by 6
  32. 2025ConeGS: Error-Guided Densification Using Pixel Cones for Improved Reconstruction With Fewer Primitivescited by 6
  33. 2023Deep Learning on Object-centric 3D Neural Fieldscited by 5
  34. 2024SAID-NeRF: Segmentation-AIDed NeRF for Depth Completion of Transparent Objectscited by 5
  35. 2025Uncertainty-Aware Normal-Guided Gaussian Splatting for Surface Reconstruction from Sparse Image Sequencescited by 5
  36. 2025Peering into the Unknown: Active View Selection with Neural Uncertainty Maps for 3D Reconstructioncited by 5
  37. 2023InstantAvatar: Efficient 3D Head Reconstruction via Surface Renderingcited by 4
  38. 2023L0-Sampler: An L0 Model Guided Volume Sampling for NeRFcited by 4

50 most cited of 90 All 90 (JSON)