mlsanityData to 7 Oct 2026

LRM: Large Reconstruction Model for Single Image to 3D

arXiv 2311.04400 ↗First posted 8 Nov 2023cs.CV cs.AI cs.GRcited by 834

Not on the map. Why?

Cited by 194 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose the first Large Reconstruction Model (LRM) that predicts the 3D model of an object from a single input image within just 5 seconds. In contrast to many previous methods that are trained on small-scale datasets such as ShapeNet in a category-specific fashion, LRM adopts a highly scalable transformer-based architecture with 500 million learnable parameters to directly predict a neural radiance field (NeRF) from the input image. We train our model in an end-to-end manner on massive multi-view data containing around 1 million objects, including both synthetic renderings from Objaverse and real captures from MVImgNet. This combination of a high-capacity model and large-scale training data empowers our model to be highly generalizable and produce high-quality 3D reconstructions from various testing inputs, including real-world in-the-wild captures and images created by generative models. Video demos and interactable 3D meshes can be found on our LRM project webpage: https://yiconghong.me/LRM.

Key facts. Cited by 834 papers in the map (data through 7 Oct 2026). Builds on 89 of its 102 references that are in the map. First posted on arXiv 8 Nov 2023.

Builds on

89 of 102 references.

References · 89

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  5. 2020Language Models are Few-Shot Learnerscited by 32,199
  6. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  7. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  8. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  9. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  10. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  11. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  3. 2022Scalable Diffusion Models with Transformerscited by 5,931
  4. 2016Layer Normalizationcited by 5,579
  5. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,304
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  9. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  10. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  11. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  13. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  14. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  15. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  16. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  17. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  18. 2019LXMERT: Learning Cross-Modality Encoder Representations from Transformerscited by 1,548
  19. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  20. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  21. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  22. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  23. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  24. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  25. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  26. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  27. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  28. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 961
  29. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  30. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  31. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  32. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  33. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 649
  34. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  35. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 646
  36. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  37. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  38. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 24; 2024: 275; 2025: 300; 2026: 235.

834 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. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  4. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  5. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  6. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  7. 2024InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Modelscited by 421
  8. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  9. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  10. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  11. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  12. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
38 more
  1. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  2. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  3. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  4. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  5. 2024TripoSR: Fast 3D Object Reconstruction from a Single Imagecited by 227
  6. 2024CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Modelcited by 214
  7. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213
  8. 2024Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformercited by 210
  9. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  10. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 191
  11. 20234D-fy: Text-to-4D Generation Using Hybrid Score Distillation Samplingcited by 184
  12. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  13. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  14. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  15. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  16. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  17. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 160
  18. 2025Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Materialcited by 157
  19. 2024VD3D: Taming Large Video Diffusion Transformers for 3D Camera Controlcited by 156
  20. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  21. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 143
  22. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  23. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  24. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  25. 2023SparseGS: Sparse View Synthesis using 3D Gaussian Splattingcited by 134
  26. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 132
  27. 2024CraftsMan3D: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refinercited by 120
  28. 2025Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Detailscited by 120
  29. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117
  30. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  31. 2024MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generationcited by 113
  32. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  33. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  34. 20244Diffusion: Multi-view Video Diffusion Model for 4D Generationcited by 104
  35. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  36. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  37. 2025CAST: Component-Aligned 3D Scene Reconstruction from an RGB Imagecited by 101
  38. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100

50 most cited of 834 All 834 (JSON)