mlsanityData to 7 Oct 2026

GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting

arXiv 2404.19702 ↗First posted 30 Apr 2024cs.CVcited by 344

Not on the map. Why?

Cited by 56 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose GS-LRM, a scalable large reconstruction model that can predict high-quality 3D Gaussian primitives from 2-4 posed sparse images in 0.23 seconds on single A100 GPU. Our model features a very simple transformer-based architecture; we patchify input posed images, pass the concatenated multi-view image tokens through a sequence of transformer blocks, and decode final per-pixel Gaussian parameters directly from these tokens for differentiable rendering. In contrast to previous LRMs that can only reconstruct objects, by predicting per-pixel Gaussians, GS-LRM naturally handles scenes with large variations in scale and complexity. We show that our model can work on both object and scene captures by training it on Objaverse and RealEstate10K respectively. In both scenarios, the models outperform state-of-the-art baselines by a wide margin. We also demonstrate applications of our model in downstream 3D generation tasks. Our project webpage is available at: https://sai-bi.github.io/project/gs-lrm/ .

Key facts. Cited by 344 papers in the map (data through 7 Oct 2026). Builds on 58 of its 74 references that are in the map. First posted on arXiv 30 Apr 2024.

Builds on

58 of 74 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  7. 2016Layer Normalizationcited by 5,579
  8. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  9. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  10. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  11. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  12. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
38 more
  1. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  4. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  5. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  6. 2017Mixed Precision Trainingcited by 1,135
  7. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  8. 2020Neural Sparse Voxel Fieldscited by 959
  9. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  10. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  11. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  12. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  13. 2020Convolutional Occupancy Networkscited by 760
  14. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  15. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  16. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  17. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  18. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  19. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  20. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  21. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  22. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  23. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  24. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  25. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  26. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  27. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  28. 2019Neural Point-Based Graphicscited by 326
  29. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
  30. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  31. 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 238
  32. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  33. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  34. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  35. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  36. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  37. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  38. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 77; 2025: 143; 2026: 124.

344 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  3. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  4. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  5. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  6. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  7. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  8. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  9. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  10. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  11. 2025Test-Time Training Done Rightcited by 121
  12. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
38 more
  1. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  2. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  3. 2025Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attentioncited by 103
  4. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 100
  5. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 98
  6. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  7. 20243D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunitiescited by 77
  8. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  9. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  10. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  11. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 72
  12. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  13. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
  14. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 62
  15. 2025Bolt3D: Generating 3D Scenes in Secondscited by 57
  16. 2024SCube: Instant Large-Scale Scene Reconstruction using VoxSplatscited by 56
  17. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusioncited by 55
  18. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  19. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  20. 2024InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Modelscited by 53
  21. 2024STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenescited by 53
  22. 2025Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatarscited by 52
  23. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Textcited by 50
  24. 2024DiffGS: Functional Gaussian Splatting Diffusioncited by 50
  25. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generationcited by 49
  26. 2024Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videoscited by 48
  27. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  28. 2024Instant3dit: Multiview Inpainting for Fast Editing of 3D Objectscited by 43
  29. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  30. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  31. 2025VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Predictioncited by 41
  32. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 40
  33. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 39
  34. 2024Physically Compatible 3D Object Modeling from a Single Imagecited by 38
  35. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 38
  36. 2025FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesiscited by 37
  37. 2025Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillationcited by 37
  38. 2024GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusioncited by 36

50 most cited of 344 All 344 (JSON)