mlsanityData to 14 Oct 2026

VGGT: Visual Geometry Grounded Transformer

arXiv 2503.11651 ↗First posted 14 Mar 2025cs.CVcited by 1,539

Not on the map. Why?

Cited by 100 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.

Key facts. Cited by 1,539 papers in the map (data through 14 Oct 2026). Builds on 116 of its 152 references that are in the map. First posted on arXiv 14 Mar 2025.

Builds on

116 of 152 references.

References · 116

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  6. 2023GPT-4 Technical Reportcited by 18,396
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  12. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  3. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  4. 2021Vision Transformers for Dense Predictioncited by 1,803
  5. 2021ViViT: A Video Vision Transformercited by 1,620
  6. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2024Depth Anything V2cited by 1,422
  10. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  11. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  12. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  13. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  14. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  15. 2023Vision Transformers Need Registerscited by 871
  16. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  17. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  18. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  19. 2021Going deeper with Image Transformerscited by 764
  20. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  21. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  22. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  23. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  24. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  25. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  26. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  27. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  28. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  29. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  30. 2023CoTracker: It is Better to Track Togethercited by 522
  31. 2024FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precisioncited by 519
  32. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  33. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  34. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  35. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  36. 2022Kubric: A scalable dataset generatorcited by 381
  37. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  38. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364

50 most cited of 116 All 116 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 456; 2026: 1083.

1,539 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  2. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  3. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  4. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  5. 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligencecited by 217
  6. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  7. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 167
  8. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 166
  9. 2025Streaming 4D Visual Geometry Transformercited by 161
  10. 2026Advancing Open-source World Modelscited by 154
  11. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  12. 2025Video World Models with Long-term Spatial Memorycited by 136
38 more
  1. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 134
  2. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
  3. 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priorscited by 120
  4. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  5. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 103
  6. 2025FastVGGT: Training-Free Acceleration of Visual Geometry Transformercited by 98
  7. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  8. 2025SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Modelscited by 90
  9. 2025JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigationcited by 89
  10. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 87
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 84
  12. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 82
  13. 2025Scaling Spatial Intelligence with Multimodal Foundation Modelscited by 82
  14. 2026PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulationcited by 82
  15. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 77
  16. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 77
  17. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 71
  18. 20253DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understandingcited by 70
  19. 2025WoW: Towards a World omniscient World model Through Embodied Interactioncited by 67
  20. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  21. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 62
  22. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understandingcited by 58
  23. 2026InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streamscited by 56
  24. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 55
  25. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 54
  26. 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a Timecited by 54
  27. 2025Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Modelscited by 52
  28. 2025Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraftcited by 52
  29. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 51
  30. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 51
  31. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 49
  32. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 46
  33. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  34. 2025Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representationscited by 45
  35. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  36. 2025How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspectivecited by 43
  37. 2026Image Generators are Generalist Vision Learnerscited by 43
  38. 2025PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generationcited by 41

50 most cited of 1,539 All 1,539 (JSON)