mlsanityData to 14 Oct 2026

GeoNeRF: Generalizing NeRF with Geometry Priors

arXiv 2111.13539 ↗First posted 26 Nov 2021cs.CVcited by 196

Not on the map. Why?

Abstract (arXiv)

We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cascaded cost volumes for each nearby source view. Then, using a Transformer-based attention mechanism and the cascaded cost volumes, the renderer infers geometry and appearance, and renders detailed images via classical volume rendering techniques. This architecture, in particular, allows sophisticated occlusion reasoning, gathering information from consistent source views. Moreover, our method can easily be fine-tuned on a single scene, and renders competitive results with per-scene optimized neural rendering methods with a fraction of computational cost. Experiments show that GeoNeRF outperforms state-of-the-art generalizable neural rendering models on various synthetic and real datasets. Lastly, with a slight modification to the geometry reasoner, we also propose an alternative model that adapts to RGBD images. This model directly exploits the depth information often available thanks to depth sensors. The implementation code is available at https://www.idiap.ch/paper/geonerf.

Key facts. Cited by 196 papers in the map (data through 14 Oct 2026). Builds on 46 of its 64 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

46 of 64 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  8. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  9. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  10. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  11. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  12. 2021Volume Rendering of Neural Implicit Surfacescited by 996
34 more
  1. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  2. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  3. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  4. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  5. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  6. 2020GRAF: Generative Radiance Fields for 3D-Aware Image Synthesiscited by 689
  7. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  8. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  9. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  10. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
  11. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  12. 2019Neural Point-Based Graphicscited by 327
  13. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  14. 2019DeepView: View Synthesis with Learned Gradient Descentcited by 253
  15. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  16. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  17. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  18. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  19. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  20. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  21. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  22. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  23. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  24. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  25. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  26. 2019Neural Rerendering in the Wildcited by 121
  27. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  28. 2019Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volumecited by 59
  29. 2019Learning a Neural 3D Texture Space from 2D Exemplarscited by 53
  30. 2021NeRF in detail: Learning to sample for view synthesiscited by 35
  31. 2020Adversarial Texture Optimization from RGB-D Scanscited by 30
  32. 2021Neural Radiance Fields Approach to Deep Multi-View Photometric Stereocited by 25
  33. 2020RGBD-Net: Predicting color and depth images for novel views synthesiscited by 11
  34. 2021NeuralMVS: Bridging Multi-View Stereo and Novel View Synthesiscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 15; 2023: 67; 2024: 66; 2025: 31; 2026: 15.

196 papers.

Sort:

By area:

  1. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  2. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  3. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 587
  4. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  5. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  6. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 349
  7. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  8. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 279
  9. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  10. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  11. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  12. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 158
38 more
  1. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  2. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  3. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 139
  4. 2022Generalizable Patch-Based Neural Renderingcited by 122
  5. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 118
  6. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  7. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 116
  8. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 114
  9. 2021Light Field Neural Renderingcited by 108
  10. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  11. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 104
  12. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  13. 2023SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collectionscited by 72
  14. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusioncited by 72
  15. 2022NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenescited by 71
  16. 2023MuRF: Multi-Baseline Radiance Fieldscited by 71
  17. 2024Advances in 3D Generation: A Surveycited by 63
  18. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  19. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  20. 20223DDesigner: Towards Photorealistic 3D Object Generation and Editing with Text-guided Diffusion Modelscited by 57
  21. 2023Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenescited by 55
  22. 2024LaRa: Efficient Large-Baseline Radiance Fieldscited by 55
  23. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  24. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 55
  25. 2023Representing Volumetric Videos as Dynamic MLP Mapscited by 51
  26. 2024DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensuscited by 51
  27. 2023Explicit Correspondence Matching for Generalizable Neural Radiance Fieldscited by 46
  28. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  29. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40
  30. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstructioncited by 39
  31. 20243DRealCar: An In-the-wild RGB-D Car Dataset with 360-degree Viewscited by 39
  32. 2022One-shot Implicit Animatable Avatars with Model-based Priorscited by 38
  33. 2023Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairscited by 37
  34. 2025Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splattingcited by 36
  35. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  36. 2024DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Featurescited by 33
  37. 2023A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstructioncited by 32
  38. 2024Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstructioncited by 32

50 most cited of 196 All 196 (JSON)