mlsanityData to 14 Oct 2026

ReconFusion: 3D Reconstruction with Diffusion Priors

arXiv 2312.02981 ↗First posted 5 Dec 2023cs.CVcited by 318

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However, recovering a high-quality NeRF typically requires tens to hundreds of input images, resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets, which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets, including forward-facing and 360-degree scenes, demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches.

Key facts. Cited by 318 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 67 of its 74 references that are in the map. First posted on arXiv 5 Dec 2023.

Builds on

67 of 74 references.

Closest ancestors · 15

Same direction, newest first

  1. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  2. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
  3. 2023HoloFusion: Towards Photo-realistic 3D Generative Modeling28 Aug
  4. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Data13 Jun
  5. 2023DreamSparse: Escaping from Plato's Cave with 2D Frozen Diffusion Model Given Sparse Views6 Jun
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation25 May
  7. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Models5 Apr
  8. 2023Consistent View Synthesis with Pose-Guided Diffusion Models30 Mar
  9. 2023HoloDiffusion: Training a 3D Diffusion Model using 2D Images29 Mar
  10. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar
  11. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Models23 Feb
  12. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation1 Dec
3 more
  1. 2022Magic3D: High-Resolution Text-to-3D Content Creation18 Nov
  2. 2022Novel View Synthesis with Diffusion Models6 Oct
  3. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep

Other references · 52

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  9. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  10. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  12. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
38 more
  1. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 785
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  3. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  4. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  5. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  6. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  7. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  8. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  9. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 484
  10. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  11. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  12. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  13. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
  14. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 302
  15. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  16. 2023SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesiscited by 247
  17. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  18. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  19. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  20. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  21. 2015DeepStereo: Learning to Predict New Views from the World's Imagerycited by 185
  22. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  23. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 180
  24. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  25. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  26. 2023State of the Art on Diffusion Models for Visual Computingcited by 127
  27. 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
  28. 2022Generalizable Patch-Based Neural Renderingcited by 122
  29. 20163D Shape Induction from 2D Views of Multiple Objectscited by 121
  30. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  31. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  32. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  33. 2022Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Imagecited by 55
  34. 2023GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistencycited by 54
  35. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  36. 2023SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutionscited by 44
  37. 2023ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fieldscited by 43
  38. 2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 114; 2025: 117; 2026: 86.

318 papers.

Sort:

By area:

  1. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  2. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  3. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  4. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  5. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 232
  6. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 182
  7. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 161
  8. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  9. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  10. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  11. 2024Recent Advances in 3D Gaussian Splattingcited by 131
  12. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 125
38 more
  1. 2024DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representationcited by 123
  2. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 118
  3. 2024Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesiscited by 117
  4. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  5. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 116
  6. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 109
  7. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  8. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 106
  9. 2025Cameras as Relative Positional Encodingcited by 105
  10. 2025Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generationcited by 101
  11. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  12. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 95
  13. 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
  14. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 89
  15. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  16. 2024Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splattingcited by 74
  17. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 70
  18. 2024ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuningcited by 70
  19. 2024SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Drivingcited by 69
  20. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 68
  21. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 67
  22. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  23. 2024Controlling Space and Time with Diffusion Modelscited by 66
  24. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  25. 2023SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Explorationcited by 62
  26. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplatscited by 60
  27. 2024GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splattingcited by 59
  28. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  29. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  30. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  31. 2024LaRa: Efficient Large-Baseline Radiance Fieldscited by 55
  32. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 55
  33. 2024FreeVS: Generative View Synthesis on Free Driving Trajectorycited by 53
  34. 2024GenXD: Generating Any 3D and 4D Scenescited by 50
  35. 2024StreetCrafter: Street View Synthesis with Controllable Video Diffusion Modelscited by 49
  36. 2024PhyRecon: Physically Plausible Neural Scene Reconstructioncited by 45
  37. 2024EG4D: Explicit Generation of 4D Object without Score Distillationcited by 45
  38. 2024PhysMotion: Physics-Grounded Dynamics From a Single Imagecited by 45

50 most cited of 318 All 318 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
  2. 2025DT-NeRF: A Diffusion and Transformer-Based Optimization Approach for Neural Radiance Fields in 3D Reconstruction
  3. 2023Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction
  4. 2024ID-NeRF: Indirect Diffusion-guided Neural Radiance Fields for Generalizable View Synthesis
  5. 2022NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
  6. 2024Generative Lifting of Multiview to 3D from Unknown Pose: Wrapping NeRF inside Diffusion
  7. 2023Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views
  8. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusion