mlsanityData to 7 Oct 2026

pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction

arXiv 2312.12337 ↗First posted 19 Dec 2023cs.CV cs.LGcited by 668

Not on the map. Why?

Cited by 78 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce pixelSplat, a feed-forward model that learns to reconstruct 3D radiance fields parameterized by 3D Gaussian primitives from pairs of images. Our model features real-time and memory-efficient rendering for scalable training as well as fast 3D reconstruction at inference time. To overcome local minima inherent to sparse and locally supported representations, we predict a dense probability distribution over 3D and sample Gaussian means from that probability distribution. We make this sampling operation differentiable via a reparameterization trick, allowing us to back-propagate gradients through the Gaussian splatting representation. We benchmark our method on wide-baseline novel view synthesis on the real-world RealEstate10k and ACID datasets, where we outperform state-of-the-art light field transformers and accelerate rendering by 2.5 orders of magnitude while reconstructing an interpretable and editable 3D radiance field.

Key facts. Cited by 668 papers in the map (data through 7 Oct 2026). Builds on 52 of its 61 references that are in the map. First posted on arXiv 19 Dec 2023.

Builds on

52 of 61 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  5. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  8. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  9. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  10. 2021Vision Transformers for Dense Predictioncited by 1,789
  11. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
38 more
  1. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  2. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  7. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  9. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  11. 2021Neural Fields in Visual Computing and Beyondcited by 539
  12. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 401
  13. 2021Advances in Neural Renderingcited by 365
  14. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  15. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 330
  16. 2019Neural Point-Based Graphicscited by 326
  17. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  18. 2020Single-View View Synthesis with Multiplane Imagescited by 263
  19. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 239
  20. 2020Free View Synthesiscited by 231
  21. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 222
  22. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  23. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  24. 2019Pushing the Boundaries of View Extrapolation with Multiplane Imagescited by 191
  25. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  26. 2021Point-Based Neural Rendering with Per-View Optimizationcited by 188
  27. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  28. 2022Generalizable Patch-Based Neural Renderingcited by 121
  29. 2020Epipolar Transformerscited by 117
  30. 2023Viewset Diffusion: (0-)Image-Conditioned 3D Generative Models from 2D Datacited by 113
  31. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  32. 2021Light Field Neural Renderingcited by 108
  33. 2022Vision Transformer for NeRF-Based View Synthesis from a Single Input Imagecited by 104
  34. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 103
  35. 2018RenderNet: A deep convolutional network for differentiable rendering from 3D shapescited by 42
  36. 2023FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flowcited by 38
  37. 2016Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequencescited by 34
  38. 2022Volume Rendering Digest (for NeRF)cited by 31

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 158; 2025: 251; 2026: 258.

668 papers.

Sort:

By area:

  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  3. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  4. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  5. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  6. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  7. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  9. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  10. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  11. 2024A Survey on 3D Gaussian Splattingcited by 221
  12. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
38 more
  1. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  2. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  3. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  4. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  5. 2024CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generationcited by 163
  6. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  7. 2024GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Predictioncited by 155
  8. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  9. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  10. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  11. 2024Recent Advances in 3D Gaussian Splattingcited by 130
  12. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  13. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  14. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  15. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  16. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  17. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  18. 20243D Gaussian as a New Era: A Surveycited by 102
  19. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
  20. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  21. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  22. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 86
  23. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  24. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
  25. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  26. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  27. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  28. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
  29. 2024TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformerscited by 71
  30. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
  31. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  32. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  33. 2025DropGaussian: Structural Regularization for Sparse-view Gaussian Splattingcited by 65
  34. 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 62
  35. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  36. 2024SpotlessSplats: Ignoring Distractors in 3D Gaussian Splattingcited by 61
  37. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 60
  38. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 60

50 most cited of 668 All 668 (JSON)