mlsanityData to 7 Oct 2026

MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo

arXiv 2103.15595 ↗First posted 29 Mar 2021cs.CVcited by 735

Not on the map. Why?

Cited by 59 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present MVSNeRF, a novel neural rendering approach that can efficiently reconstruct neural radiance fields for view synthesis. Unlike prior works on neural radiance fields that consider per-scene optimization on densely captured images, we propose a generic deep neural network that can reconstruct radiance fields from only three nearby input views via fast network inference. Our approach leverages plane-swept cost volumes (widely used in multi-view stereo) for geometry-aware scene reasoning, and combines this with physically based volume rendering for neural radiance field reconstruction. We train our network on real objects in the DTU dataset, and test it on three different datasets to evaluate its effectiveness and generalizability. Our approach can generalize across scenes (even indoor scenes, completely different from our training scenes of objects) and generate realistic view synthesis results using only three input images, significantly outperforming concurrent works on generalizable radiance field reconstruction. Moreover, if dense images are captured, our estimated radiance field representation can be easily fine-tuned; this leads to fast per-scene reconstruction with higher rendering quality and substantially less optimization time than NeRF.

Key facts. Cited by 735 papers in the map (data through 7 Oct 2026). Builds on 29 of its 57 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

29 of 57 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 904
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  8. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 750
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  11. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  12. 2020State of the Art on Neural Renderingcited by 276
17 more
  1. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  2. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  3. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  4. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  5. 2016View Synthesis by Appearance Flowcited by 172
  6. 2020DeRF: Decomposed Radiance Fieldscited by 163
  7. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  8. 2019Point-Based Multi-View Stereo Networkcited by 147
  9. 2016Learning-Based View Synthesis for Light Field Camerascited by 145
  10. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  11. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  12. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  13. 2018Extreme View Synthesiscited by 94
  14. 2020SofGAN: A Portrait Image Generator with Dynamic Stylingcited by 65
  15. 2017Learning to Synthesize a 4D RGBD Light Field from a Single Imagecited by 60
  16. 2019A Neural Rendering Framework for Free-Viewpoint Relightingcited by 26
  17. 2018Deep Surface Light Fieldscited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 31; 2022: 110; 2023: 212; 2024: 189; 2025: 113; 2026: 80.

735 papers.

Sort:

By area:

  1. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  2. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  3. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  4. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 732
  5. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  6. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  7. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  8. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  10. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  11. 2021Neural Fields in Visual Computing and Beyondcited by 539
  12. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
38 more
  1. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  2. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  3. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  4. 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
  5. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  6. 2022Fast Dynamic Radiance Fields with Time-Aware Neural Voxelscited by 344
  7. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  8. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  9. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  10. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  11. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  12. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  13. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  14. 2021Urban Radiance Fieldscited by 263
  15. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  16. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  17. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  18. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  19. 2022DynIBaR: Neural Dynamic Image-Based Renderingcited by 224
  20. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  21. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  22. 2022NeRF-Editing: Geometry Editing of Neural Radiance Fieldscited by 216
  23. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  24. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  25. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  26. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  27. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  28. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  29. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  30. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  31. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  32. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  33. 2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
  34. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  35. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  36. 2022Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-timecited by 164
  37. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  38. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160

50 most cited of 735 All 735 (JSON)