mlsanityData to 7 Oct 2026

Point-NeRF: Point-based Neural Radiance Fields

arXiv 2201.08845 ↗First posted 21 Jan 2022cs.CVcited by 503

Not on the map. Why?

Abstract (arXiv)

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct scene geometry via direct network inference. Point-NeRF combines the advantages of these two approaches by using neural 3D point clouds, with associated neural features, to model a radiance field. Point-NeRF can be rendered efficiently by aggregating neural point features near scene surfaces, in a ray marching-based rendering pipeline. Moreover, Point-NeRF can be initialized via direct inference of a pre-trained deep network to produce a neural point cloud; this point cloud can be finetuned to surpass the visual quality of NeRF with 30X faster training time. Point-NeRF can be combined with other 3D reconstruction methods and handles the errors and outliers in such methods via a novel pruning and growing mechanism. The experiments on the DTU, the NeRF Synthetics , the ScanNet and the Tanks and Temples datasets demonstrate Point-NeRF can surpass the existing methods and achieve the state-of-the-art results.

Key facts. Cited by 503 papers in the map (data through 7 Oct 2026). Builds on 47 of its 68 references that are in the map. First posted on arXiv 21 Jan 2022.

Builds on

47 of 68 references.

References · 47

  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. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  7. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  9. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  11. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  12. 2020Neural Sparse Voxel Fieldscited by 959
35 more
  1. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  4. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  5. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  6. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  7. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  8. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  9. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  10. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  11. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 688
  12. 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 672
  13. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  14. 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 465
  15. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  16. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  17. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  18. 2019Neural Point-Based Graphicscited by 326
  19. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  20. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  21. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  22. 2021HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fieldscited by 210
  23. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 206
  24. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  25. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
  26. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  27. 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
  28. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  29. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  30. 2019Neural Rerendering in the Wildcited by 121
  31. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  32. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  33. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  34. 2017SfM-Net: Learning of Structure and Motion from Videocited by 89
  35. 2018MVPNet: Multi-View Point Regression Networks for 3D Object Reconstruction from A Single Imagecited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 41; 2023: 157; 2024: 187; 2025: 85; 2026: 33.

503 papers.

Sort:

By area:

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  4. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  5. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  6. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  7. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  8. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  9. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  10. 2023PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamicscited by 368
  11. 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 365
  12. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
38 more
  1. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  2. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  3. 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 341
  4. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
  5. 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 308
  6. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  7. 2023GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussianscited by 256
  8. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  9. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 232
  10. 2023LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenescited by 228
  11. 2024Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussianscited by 225
  12. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
  13. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 208
  14. 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 205
  15. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  16. 20233DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splattingcited by 195
  17. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  18. 2024CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussianscited by 190
  19. 2022PointAvatar: Deformable Point-based Head Avatars from Videoscited by 183
  20. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  21. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  22. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 171
  23. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  24. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  25. 2023TensoIR: Tensorial Inverse Renderingcited by 166
  26. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  27. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  28. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  29. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
  30. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  31. 2023CompGS: Smaller and Faster Gaussian Splatting with Vector Quantizationcited by 127
  32. 2023Drivable 3D Gaussian Avatarscited by 120
  33. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  34. 2023F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectoriescited by 118
  35. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  36. 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 111
  37. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  38. 2023Human Gaussian Splatting: Real-time Rendering of Animatable Avatarscited by 105

50 most cited of 503 All 503 (JSON)