mlsanityData to 7 Oct 2026

SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

arXiv 2212.00792 ↗First posted 1 Dec 2022cs.CV cs.GRcited by 216

Not on the map. Why?

Cited by 100 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but fail to generate unseen regions or handle uncertainty under large viewpoint changes. Alternate methods treat this as a (probabilistic) 2D synthesis task, and while they can generate plausible 2D images, they do not infer a consistent underlying 3D. However, we find that this trade-off between 3D consistency and probabilistic image generation does not need to exist. In fact, we show that geometric consistency and generative inference can be complementary in a mode-seeking behavior. By distilling a 3D consistent scene representation from a view-conditioned latent diffusion model, we are able to recover a plausible 3D representation whose renderings are both accurate and realistic. We evaluate our approach across 51 categories in the CO3D dataset and show that it outperforms existing methods, in both distortion and perception metrics, for sparse-view novel view synthesis.

Key facts. Cited by 216 papers in the map (data through 7 Oct 2026). Builds on 44 of its 57 references that are in the map. First posted on arXiv 1 Dec 2022.

Builds on

44 of 57 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 2020Denoising Diffusion Implicit Modelscited by 9,655
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  10. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  12. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
32 more
  1. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  2. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  3. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  4. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  5. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  6. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  7. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  8. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  9. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 614
  10. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  11. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  12. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  13. 2022Novel View Synthesis with Diffusion Modelscited by 299
  14. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  15. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  16. 2017Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistencycited by 177
  17. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  18. 2016View Synthesis by Appearance Flowcited by 172
  19. 2018Escaping Plato's Cave: 3D Shape From Adversarial Renderingcited by 170
  20. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  21. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  22. 2022Generalizable Patch-Based Neural Renderingcited by 121
  23. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  24. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  25. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  26. 2020SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Imagescited by 68
  27. 2021Shelf-Supervised Mesh Prediction in the Wildcited by 65
  28. 2015Multi-view 3D Models from Single Images with a Convolutional Networkcited by 57
  29. 2022FWD: Real-time Novel View Synthesis with Forward Warping and Depthcited by 39
  30. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  31. 2021Differentiable Stereopsis: Meshes from multiple views using differentiable renderingcited by 26
  32. 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 71; 2024: 86; 2025: 44; 2026: 15.

216 papers.

Sort:

By area:

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  3. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  4. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 682
  5. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  6. 2023HexPlane: A Fast Representation for Dynamic Scenescited by 582
  7. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  8. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  9. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  10. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  11. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  12. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
38 more
  1. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  2. 2023ImageDream: Image-Prompt Multi-view Diffusion for 3D Generationcited by 256
  3. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  4. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  5. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 217
  6. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  7. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  8. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
  9. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  10. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 160
  11. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  12. 2023State of the Art on Diffusion Models for Visual Computingcited by 126
  13. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  14. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  15. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  16. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  17. 2023HiFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidancecited by 109
  18. 2023TADA! Text to Animatable Digital Avatarscited by 109
  19. 2024RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusioncited by 109
  20. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  21. 2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
  22. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 91
  23. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  24. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  25. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesiscited by 84
  26. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Modelscited by 79
  27. 2023Nerfbusters: Removing Ghostly Artifacts from Casually Captured NeRFscited by 76
  28. 2023Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clipscited by 73
  29. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72
  30. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 67
  31. 2023NeRFiller: Completing Scenes via Generative 3D Inpaintingcited by 62
  32. 2024SPAD : Spatially Aware Multiview Diffuserscited by 62
  33. 2024GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splattingcited by 59
  34. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  35. 2024ViewDiff: 3D-Consistent Image Generation with Text-to-Image Modelscited by 57
  36. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  37. 2024DiG: Scalable and Efficient Diffusion Models with Gated Linear Attentioncited by 56
  38. 2023RoomDreamer: Text-Driven 3D Indoor Scene Synthesis with Coherent Geometry and Texturecited by 53

50 most cited of 216 All 216 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
  2. 2026Predicting 3D structure by latent posterior sampling
  3. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videos
  4. 2023WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
  5. 2026Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
  6. 2025Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion
  7. 2024ViewFusion: Learning Composable Diffusion Models for Novel View Synthesis
  8. 2026VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis