mlsanityData to 14 Oct 2026

Differentiable Point-Based Radiance Fields for Efficient View Synthesis

arXiv 2205.14330 ↗First posted 28 May 2022cs.CV cs.GRcited by 86

Not on the map. Why?

Abstract (arXiv)

We propose a differentiable rendering algorithm for efficient novel view synthesis. By departing from volume-based representations in favor of a learned point representation, we improve on existing methods more than an order of magnitude in memory and runtime, both in training and inference. The method begins with a uniformly-sampled random point cloud and learns per-point position and view-dependent appearance, using a differentiable splat-based renderer to evolve the model to match a set of input images. Our method is up to 300x faster than NeRF in both training and inference, with only a marginal sacrifice in quality, while using less than 10~MB of memory for a static scene. For dynamic scenes, our method trains two orders of magnitude faster than STNeRF and renders at near interactive rate, while maintaining high image quality and temporal coherence even without imposing any temporal-coherency regularizers.

Key facts. Cited by 86 papers in the map (data through 14 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 28 May 2022.

Builds on

27 of 48 references.

References · 27

  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  3. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  4. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  5. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  6. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  7. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
  8. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 511
  9. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  10. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
  11. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  12. 2019Neural Point-Based Graphicscited by 327
15 more
  1. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  2. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
  3. 2021DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networkscited by 232
  4. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
  5. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  6. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  7. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 190
  8. 2021Editable Free-viewpoint Video Using a Layered Neural Representationcited by 148
  9. 2019Neural Rerendering in the Wildcited by 121
  10. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  11. 2020DRWR: A Differentiable Renderer without Rendering for Unsupervised 3D Structure Learning from Silhouette Imagescited by 35
  12. 2021Neural BRDF Representation and Importance Samplingcited by 28
  13. 2020Invertible Neural BRDF for Object Inverse Renderingcited by 17
  14. 2021VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Fieldcited by 14
  15. 2021ADOP: Approximate Differentiable One-Pixel Point Renderingcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 31; 2024: 28; 2025: 21; 2026: 3.

86 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
  3. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  4. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
  5. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 347
  6. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 221
  7. 2023Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particlecited by 211
  8. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  9. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  10. 20244D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis for Dynamic Scenescited by 189
  11. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  12. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 184
38 more
  1. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  2. 2023Relightable 3D Gaussians: Realistic Point Cloud Relighting with BRDF Decomposition and Ray Tracingcited by 142
  3. 2023DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splattingcited by 124
  4. 2023GART: Gaussian Articulated Template Modelscited by 121
  5. 2024ContextGS: Compact 3D Gaussian Splatting with Anchor Level Context Modelcited by 102
  6. 2023GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesiscited by 95
  7. 2024GES: Generalized Exponential Splatting for Efficient Radiance Field Renderingcited by 92
  8. 20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
  9. 20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
  10. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 74
  11. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  12. 2023Gaussian Shell Maps for Efficient 3D Human Generationcited by 61
  13. 2023Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstructioncited by 61
  14. 2022Masked Wavelet Representation for Compact Neural Radiance Fieldscited by 57
  15. 2024Gaussian Splatting: 3D Reconstruction and Novel View Synthesis, a Reviewcited by 41
  16. 2023Binary Radiance Fieldscited by 40
  17. 2022ClimateNeRF: Extreme Weather Synthesis in Neural Radiance Fieldcited by 37
  18. 2023Dynamic Point Fieldscited by 37
  19. 2024TRIPS: Trilinear Point Splatting for Real-Time Radiance Field Renderingcited by 33
  20. 2023Human101: Training 100+FPS Human Gaussians in 100s from 1 Viewcited by 32
  21. 2024HEMGS: A Hybrid Entropy Model for 3D Gaussian Splatting Data Compressioncited by 31
  22. 2023SurfelNeRF: Neural Surfel Radiance Fields for Online Photorealistic Reconstruction of Indoor Scenescited by 30
  23. 2024VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Pointscited by 29
  24. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  25. 2024EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representationcited by 27
  26. 2024GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesiscited by 25
  27. 2024Compact 3D Gaussian Splatting for Static and Dynamic Radiance Fieldscited by 25
  28. 2025LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videoscited by 24
  29. 2023Pointersect: Neural Rendering with Cloud-Ray Intersectioncited by 23
  30. 2024Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solidscited by 23
  31. 20253DGS2: Near Second-order Converging 3D Gaussian Splattingcited by 19
  32. 2025Does 3D Gaussian Splatting Need Accurate Volumetric Rendering?cited by 19
  33. 2023TriVol: Point Cloud Rendering via Triple Volumescited by 16
  34. 2023PAPR: Proximity Attention Point Renderingcited by 16
  35. 2024NeRFCodec: Neural Feature Compression Meets Neural Radiance Fields for Memory-Efficient Scene Representationcited by 16
  36. 2025DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusioncited by 15
  37. 2023VET: Visual Error Tomography for Point Cloud Completion and High-Quality Neural Renderingcited by 14
  38. 2025When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Renderingcited by 14

50 most cited of 86 All 86 (JSON)