mlsanityData to 7 Oct 2026

MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes

arXiv 2302.12249 ↗First posted 23 Feb 2023cs.CV cs.GRcited by 215

Not on the map. Why?

Abstract (arXiv)

Neural radiance fields enable state-of-the-art photorealistic view synthesis. However, existing radiance field representations are either too compute-intensive for real-time rendering or require too much memory to scale to large scenes. We present a Memory-Efficient Radiance Field (MERF) representation that achieves real-time rendering of large-scale scenes in a browser. MERF reduces the memory consumption of prior sparse volumetric radiance fields using a combination of a sparse feature grid and high-resolution 2D feature planes. To support large-scale unbounded scenes, we introduce a novel contraction function that maps scene coordinates into a bounded volume while still allowing for efficient ray-box intersection. We design a lossless procedure for baking the parameterization used during training into a model that achieves real-time rendering while still preserving the photorealistic view synthesis quality of a volumetric radiance field.

Key facts. Cited by 215 papers in the map (data through 7 Oct 2026). Builds on 49 of its 68 references that are in the map. First posted on arXiv 23 Feb 2023.

Builds on

49 of 68 references.

References · 49

  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. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  6. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  11. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  12. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
37 more
  1. 2020Neural Sparse Voxel Fieldscited by 959
  2. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  3. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  4. 2020Convolutional Occupancy Networkscited by 760
  5. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 720
  6. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  7. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  8. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  9. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  10. 2021Mega-NeRF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughscited by 396
  11. 2021Advances in Neural Renderingcited by 365
  12. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  13. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  14. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  15. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  16. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  17. 2019Understanding Straight-Through Estimator in Training Activation Quantized Neural Netscited by 225
  18. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 215
  19. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  20. 2020Stable View Synthesiscited by 165
  21. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  22. 2022Variable Bitrate Neural Fieldscited by 116
  23. 2021Neural Lumigraph Renderingcited by 105
  24. 2022ReLU Fields: The Little Non-linearity That Couldcited by 87
  25. 2022NerfAcc: A General NeRF Acceleration Toolboxcited by 73
  26. 2021TermiNeRF: Ray Termination Prediction for Efficient Neural Renderingcited by 70
  27. 2022R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesiscited by 69
  28. 2022AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fieldscited by 68
  29. 2022Compressing Volumetric Radiance Fields to 1 MBcited by 66
  30. 2020MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Imagescited by 64
  31. 2021DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Renderingcited by 60
  32. 2022Compressing Explicit Voxel Grid Representations: fast NeRFs become also smallcited by 48
  33. 2022Real-Time Neural Light Field on Mobile Devicescited by 48
  34. 2021NeuLF: Efficient Novel View Synthesis with Neural 4D Light Fieldcited by 33
  35. 2022NeurMiPs: Neural Mixture of Planar Experts for View Synthesiscited by 23
  36. 20224K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutionscited by 23
  37. 2022SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectorycited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 54; 2024: 103; 2025: 41; 2026: 17.

215 papers.

Sort:

By area:

  1. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  2. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  3. 2023Text-to-3D using Gaussian Splattingcited by 299
  4. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 232
  5. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  6. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  7. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  8. 2024A Hierarchical 3D Gaussian Representation for Real-Time Rendering of Very Large Datasetscited by 214
  9. 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
  10. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  11. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 190
  12. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
38 more
  1. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 159
  2. 20243DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videoscited by 156
  3. 2023Compact 3D Scene Representation via Self-Organizing Gaussian Gridscited by 147
  4. 2023Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Renderingcited by 143
  5. 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 141
  6. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 138
  7. 2024Reducing the Memory Footprint of 3D Gaussian Splattingcited by 129
  8. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  9. 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 110
  10. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  11. 2023Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinementcited by 106
  12. 2023NerfAcc: Efficient Sampling Accelerates NeRFscited by 90
  13. 20243DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splattingcited by 87
  14. 2024End-to-End Rate-Distortion Optimized 3D Gaussian Representationcited by 71
  15. 2023Adaptive Shells for Efficient Neural Radiance Field Renderingcited by 69
  16. 2023HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splattingcited by 68
  17. 2024Deblurring 3D Gaussian Splattingcited by 66
  18. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  19. 2023Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedracited by 57
  20. 2024ViewDiff: 3D-Consistent Image Generation with Text-to-Image Modelscited by 57
  21. 2024Radiative Gaussian Splatting for Efficient X-ray Novel View Synthesiscited by 56
  22. 2024MesonGS: Post-training Compression of 3D Gaussians via Efficient Attribute Transformationcited by 54
  23. 2024GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplanecited by 53
  24. 2024AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstructioncited by 52
  25. 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
  26. 2023Watch Your Steps: Local Image and Scene Editing by Text Instructionscited by 50
  27. 20243D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexescited by 50
  28. 2025Triangle Splatting for Real-Time Radiance Field Renderingcited by 50
  29. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 47
  30. 2023Explicit Correspondence Matching for Generalizable Neural Radiance Fieldscited by 46
  31. 2024EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesiscited by 46
  32. 2023Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstructioncited by 43
  33. 2024SceneTeller: Language-to-3D Scene Generationcited by 43
  34. 2024Binary Opacity Grids: Capturing Fine Geometric Detail for Mesh-Based View Synthesiscited by 41
  35. 2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 41
  36. 2023Reference-guided Controllable Inpainting of Neural Radiance Fieldscited by 40
  37. 2025Swift4D:Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scenecited by 40
  38. 2024GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removalcited by 39

50 most cited of 215 All 215 (JSON)