mlsanityData to 7 Oct 2026

Splatter Image: Ultra-Fast Single-View 3D Reconstruction

arXiv 2312.13150 ↗First posted 20 Dec 2023cs.CVcited by 359

Not on the map. Why?

Cited by 52 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce the method, an ultra-efficient approach for monocular 3D object reconstruction. Splatter Image is based on Gaussian Splatting, which allows fast and high-quality reconstruction of 3D scenes from multiple images. We apply Gaussian Splatting to monocular reconstruction by learning a neural network that, at test time, performs reconstruction in a feed-forward manner, at 38 FPS. Our main innovation is the surprisingly straightforward design of this network, which, using 2D operators, maps the input image to one 3D Gaussian per pixel. The resulting set of Gaussians thus has the form an image, the Splatter Image. We further extend the method take several images as input via cross-view attention. Owning to the speed of the renderer (588 FPS), we use a single GPU for training while generating entire images at each iteration to optimize perceptual metrics like LPIPS. On several synthetic, real, multi-category and large-scale benchmark datasets, we achieve better results in terms of PSNR, LPIPS, and other metrics while training and evaluating much faster than prior works. Code, models, demo and more results are available at https://szymanowiczs.github.io/splatter-image.

Key facts. Cited by 359 papers in the map (data through 7 Oct 2026). Builds on 54 of its 62 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

54 of 62 references.

References · 54

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  10. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  11. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  12. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
38 more
  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  4. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  5. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  6. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  9. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 767
  10. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  11. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  12. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  13. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  14. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  15. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  16. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  17. 2017Neural 3D Mesh Renderercited by 437
  18. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  19. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  20. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 305
  21. 2022Novel View Synthesis with Diffusion Modelscited by 299
  22. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  23. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  24. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  25. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  26. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  27. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  28. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  29. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  30. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  31. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  32. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  33. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  34. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  35. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  36. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  37. 2021PixelSynth: Generating a 3D-Consistent Experience from a Single Imagecited by 82
  38. 2023Free3D: Consistent Novel View Synthesis without 3D Representationcited by 72

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 120; 2025: 134; 2026: 104.

359 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  3. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  4. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  5. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  6. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  7. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  8. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  9. 2024A Survey on 3D Gaussian Splattingcited by 221
  10. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  11. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  12. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
38 more
  1. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  2. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  3. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  4. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  5. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  6. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  7. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  8. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  9. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  10. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  11. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  12. 20243D Gaussian as a New Era: A Surveycited by 102
  13. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  14. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  15. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
  16. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  17. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 91
  18. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  19. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
  20. 2024TC4D: Trajectory-Conditioned Text-to-4D Generationcited by 76
  21. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  22. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  23. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  24. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  25. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
  26. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  27. 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 62
  28. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  29. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  30. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  31. 2024Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructioncited by 56
  32. 2024Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collectionscited by 56
  33. 2024HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstructioncited by 55
  34. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  35. 2024LaRa: Efficient Large-Baseline Radiance Fieldscited by 54
  36. 2024DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Inputcited by 53
  37. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 53
  38. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52

50 most cited of 359 All 359 (JSON)