mlsanityData to 7 Oct 2026

MeshLRM: Large Reconstruction Model for High-Quality Meshes

arXiv 2404.12385 ↗First posted 18 Apr 2024cs.CV cs.GRcited by 138

Not on the map. Why?

Cited by 24 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose MeshLRM, a novel LRM-based approach that can reconstruct a high-quality mesh from merely four input images in less than one second. Different from previous large reconstruction models (LRMs) that focus on NeRF-based reconstruction, MeshLRM incorporates differentiable mesh extraction and rendering within the LRM framework. This allows for end-to-end mesh reconstruction by fine-tuning a pre-trained NeRF LRM with mesh rendering. Moreover, we improve the LRM architecture by simplifying several complex designs in previous LRMs. MeshLRM's NeRF initialization is sequentially trained with low- and high-resolution images; this new LRM training strategy enables significantly faster convergence and thereby leads to better quality with less compute. Our approach achieves state-of-the-art mesh reconstruction from sparse-view inputs and also allows for many downstream applications, including text-to-3D and single-image-to-3D generation. Project page: https://sarahweiii.github.io/meshlrm/

Key facts. Cited by 138 papers in the map (data through 7 Oct 2026). Builds on 67 of its 80 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

67 of 80 references.

References · 67

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  9. 2016Layer Normalizationcited by 5,579
  10. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  11. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  12. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
38 more
  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  3. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,285
  7. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  8. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  9. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  10. 2021Volume Rendering of Neural Implicit Surfacescited by 990
  11. 2020Neural Sparse Voxel Fieldscited by 959
  12. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 834
  13. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  14. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  15. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 698
  16. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 684
  17. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  18. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  19. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  20. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  21. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 555
  22. 2023Zero123++: a Single Image to Consistent Multi-view Diffusion Base Modelcited by 516
  23. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  24. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  25. 2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
  26. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  27. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  28. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 376
  29. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  30. 2023Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Priorcited by 341
  31. 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 310
  32. 2022Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusioncited by 309
  33. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  34. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 278
  35. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  36. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  37. 2023BakedSDF: Meshing Neural SDFs for Real-Time View Synthesiscited by 220
  38. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 213

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 52; 2025: 56; 2026: 30.

138 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2025TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Modelscited by 204
  3. 2024LVSM: A Large View Synthesis Model with Minimal 3D Inductive Biascited by 178
  4. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  5. 2024MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformerscited by 140
  6. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  7. 2024MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenizationcited by 102
  8. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 100
  9. 20243DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusioncited by 100
  10. 2024Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attentioncited by 99
  11. 2024Meshtron: High-Fidelity, Artist-Like 3D Mesh Generation at Scalecited by 87
  12. 2025Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assetscited by 85
38 more
  1. 2024EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generationcited by 84
  2. 2025SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modelingcited by 76
  3. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  4. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 72
  5. 2024Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materialscited by 66
  6. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
  7. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  8. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusioncited by 55
  9. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  10. 2024HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priorscited by 54
  11. 2025DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generationcited by 49
  12. 2025SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generationcited by 44
  13. 2024Instant3dit: Multiview Inpainting for Fast Editing of 3D Objectscited by 43
  14. 2025Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attentioncited by 43
  15. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Imagescited by 41
  16. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 40
  17. 2024Physically Compatible 3D Object Modeling from a Single Imagecited by 38
  18. 2024Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cyclecited by 36
  19. 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Datacited by 35
  20. 2024GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generationcited by 35
  21. 2025ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understandingcited by 34
  22. 2025AutoPartGen: Autogressive 3D Part Generation and Discoverycited by 33
  23. 2025AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animationcited by 31
  24. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 30
  25. 2024G3R: Gradient Guided Generalizable Reconstructioncited by 29
  26. 2025Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Datasetcited by 29
  27. 2024ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillationcited by 27
  28. 2024Real3D: Scaling Up Large Reconstruction Models with Real-World Imagescited by 24
  29. 2024MVGamba: Unify 3D Content Generation as State Space Sequence Modelingcited by 23
  30. 2024RelitLRM: Generative Relightable Radiance for Large Reconstruction Modelscited by 23
  31. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  32. 2024Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketchescited by 21
  33. 2024MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Datacited by 21
  34. 2024TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshescited by 20
  35. 20243D Mesh Editing using Masked LRMscited by 17
  36. 2025UnCommon Objects in 3Dcited by 17
  37. 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fieldscited by 16
  38. 2024G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformercited by 15

50 most cited of 138 All 138 (JSON)