mlsanityData to 14 Oct 2026

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

arXiv 2403.14627 ↗First posted 21 Mar 2024cs.CVcited by 566

Not on the map. Why?

Cited by 61 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce MVSplat, an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where the cross-view feature similarities stored in the cost volume can provide valuable geometry cues to the estimation of depth. We also learn other Gaussian primitives' parameters jointly with the Gaussian centers while only relying on photometric supervision. We demonstrate the importance of the cost volume representation in learning feed-forward Gaussians via extensive experimental evaluations. On the large-scale RealEstate10K and ACID benchmarks, MVSplat achieves state-of-the-art performance with the fastest feed-forward inference speed (22~fps). More impressively, compared to the latest state-of-the-art method pixelSplat, MVSplat uses 10× fewer parameters and infers more than 2× faster while providing higher appearance and geometry quality as well as better cross-dataset generalization.

Key facts. Cited by 566 papers in the map (data through 14 Oct 2026). Builds on 41 of its 52 references that are in the map. First posted on arXiv 21 Mar 2024.

Builds on

41 of 52 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  7. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  9. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 938
  10. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
29 more
  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  2. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  3. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  4. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  7. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  8. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  9. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  10. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  11. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 327
  12. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 318
  13. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  14. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  15. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  16. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  17. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 196
  18. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  19. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  20. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  21. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  22. 2022Generalizable Patch-Based Neural Renderingcited by 122
  23. 2020Epipolar Transformerscited by 117
  24. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  25. 2023Learning to Render Novel Views from Wide-Baseline Stereo Pairscited by 104
  26. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 79
  27. 2023MuRF: Multi-Baseline Radiance Fieldscited by 71
  28. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  29. 2023Explicit Correspondence Matching for Generalizable Neural Radiance Fieldscited by 46

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 94; 2025: 222; 2026: 250.

566 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  2. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  3. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  4. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  5. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  6. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  7. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 189
  8. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 182
  9. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  10. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  11. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 144
  12. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
38 more
  1. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  2. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 125
  3. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 116
  4. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 116
  5. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 114
  6. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 109
  7. 2025Cameras as Relative Positional Encodingcited by 105
  8. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  9. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 89
  10. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 82
  11. 2024NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizercited by 79
  12. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 78
  13. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 77
  14. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 70
  15. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 67
  16. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  17. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  18. 2025DropGaussian: Structural Regularization for Sparse-view Gaussian Splattingcited by 65
  19. 2024MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splattingcited by 63
  20. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  21. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplatscited by 60
  22. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  23. 2024HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstructioncited by 57
  24. 2024InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Modelscited by 56
  25. 2024LaRa: Efficient Large-Baseline Radiance Fieldscited by 55
  26. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 53
  27. 2024Fast Feedforward 3D Gaussian Splatting Compressioncited by 52
  28. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Textcited by 50
  29. 2024Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videoscited by 49
  30. 2025VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Predictioncited by 48
  31. 2024MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenescited by 47
  32. 2024GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understandingcited by 46
  33. 2024PhysMotion: Physics-Grounded Dynamics From a Single Imagecited by 45
  34. 20243DGS-LM: Faster Gaussian-Splatting Optimization with Levenberg-Marquardtcited by 43
  35. 2024SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splattingcited by 42
  36. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 41
  37. 2025GenFusion: Closing the Loop between Reconstruction and Generation via Videoscited by 41
  38. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 40

50 most cited of 566 All 566 (JSON)