mlsanityData to 7 Oct 2026

Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering

arXiv 2106.02634 ↗First posted 4 Jun 2021cs.CV cs.AI cs.GRcited by 330

Not on the map. Why?

Cited by 55 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Inferring representations of 3D scenes from 2D observations is a fundamental problem of computer graphics, computer vision, and artificial intelligence. Emerging 3D-structured neural scene representations are a promising approach to 3D scene understanding. In this work, we propose a novel neural scene representation, Light Field Networks or LFNs, which represent both geometry and appearance of the underlying 3D scene in a 360-degree, four-dimensional light field parameterized via a neural implicit representation. Rendering a ray from an LFN requires only a single network evaluation, as opposed to hundreds of evaluations per ray for ray-marching or volumetric based renderers in 3D-structured neural scene representations. In the setting of simple scenes, we leverage meta-learning to learn a prior over LFNs that enables multi-view consistent light field reconstruction from as little as a single image observation. This results in dramatic reductions in time and memory complexity, and enables real-time rendering. The cost of storing a 360-degree light field via an LFN is two orders of magnitude lower than conventional methods such as the Lumigraph. Utilizing the analytical differentiability of neural implicit representations and a novel parameterization of light space, we further demonstrate the extraction of sparse depth maps from LFNs.

Key facts. Cited by 330 papers in the map (data through 7 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

35 of 66 references.

References · 35

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2016HyperNetworkscited by 1,003
  10. 2020Neural Sparse Voxel Fieldscited by 959
  11. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  12. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
23 more
  1. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  2. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  3. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  6. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  7. 2017Neural 3D Mesh Renderercited by 437
  8. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  9. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  10. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  11. 2020State of the Art on Neural Renderingcited by 276
  12. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  13. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  14. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  15. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  16. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 111
  17. 2021Neural Lumigraph Renderingcited by 105
  18. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  19. 2016Unsupervised Learning of 3D Structure from Imagescited by 67
  20. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  21. 2018Learning Spatial Common Sense with Geometry-Aware Recurrent Networkscited by 35
  22. 2017Interpretable Transformations with Encoder-Decoder Networkscited by 33
  23. 2015Light Field Reconstruction Using Shearlet Transformcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 53; 2023: 78; 2024: 71; 2025: 68; 2026: 49.

330 papers.

Sort:

By area:

  1. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  2. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  3. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  4. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  5. 2021Neural Fields in Visual Computing and Beyondcited by 539
  6. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  7. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 448
  8. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  9. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  10. 2022Kubric: A scalable dataset generatorcited by 373
  11. 2021Advances in Neural Renderingcited by 365
  12. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
38 more
  1. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  2. 2022Novel View Synthesis with Diffusion Modelscited by 299
  3. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  4. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  5. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  6. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  7. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  8. 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 215
  9. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  10. 2021Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulationcited by 204
  11. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  12. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  13. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  14. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  15. 2023HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Samplingcited by 173
  16. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  17. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  18. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 163
  19. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  20. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  21. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 152
  22. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  23. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  24. 2022D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Videocited by 136
  25. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  26. 2022Generalizable Patch-Based Neural Renderingcited by 121
  27. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  28. 2022Is Attention All That NeRF Needs?cited by 113
  29. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  30. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  31. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  32. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  33. 2021Light Field Neural Renderingcited by 108
  34. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 103
  35. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 97
  36. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  37. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  38. 2021LOLNeRF: Learn from One Lookcited by 84

50 most cited of 330 All 330 (JSON)