mlsanityData to 7 Oct 2026

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

arXiv 2505.12549 ↗First posted 18 May 2025cs.CVcited by 130

Not on the map. Why?

Abstract (arXiv)

We present VGGT-SLAM, a dense RGB SLAM system constructed by incrementally and globally aligning submaps created from the feed-forward scene reconstruction approach VGGT using only uncalibrated monocular cameras. While related works align submaps using similarity transforms (i.e., translation, rotation, and scale), we show that such approaches are inadequate in the case of uncalibrated cameras. In particular, we revisit the idea of reconstruction ambiguity, where given a set of uncalibrated cameras with no assumption on the camera motion or scene structure, the scene can only be reconstructed up to a 15-degrees-of-freedom projective transformation of the true geometry. This inspires us to recover a consistent scene reconstruction across submaps by optimizing over the SL(4) manifold, thus estimating 15-degrees-of-freedom homography transforms between sequential submaps while accounting for potential loop closure constraints. As verified by extensive experiments, we demonstrate that VGGT-SLAM achieves improved map quality using long video sequences that are infeasible for VGGT due to its high GPU requirements.

Key facts. Cited by 130 papers in the map (data through 7 Oct 2026). Builds on 42 of its 84 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

42 of 84 references.

References · 42

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2021Vision Transformers for Dense Predictioncited by 1,789
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  5. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  6. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  7. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  8. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  9. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  10. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  11. 2023Gaussian Splatting SLAMcited by 410
  12. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
30 more
  1. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  2. 20243D Reconstruction with Spatial Memorycited by 269
  3. 2024Global Structure-from-Motion Revisitedcited by 215
  4. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  5. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  6. 2019Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mappingcited by 181
  7. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  8. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  9. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  10. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  11. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 151
  12. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  13. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  14. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  15. 2023Accelerated Coordinate Encoding: Learning to Relocalize in Minutes using RGB and Posescited by 107
  16. 2024Clio: Real-time Task-Driven Open-Set 3D Scene Graphscited by 81
  17. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 81
  18. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  19. 2024Deep Patch Visual SLAMcited by 68
  20. 2024GeoCalib: Learning Single-image Calibration with Geometric Optimizationcited by 50
  21. 2019A General Optimization-based Framework for Global Pose Estimation with Multiple Sensorscited by 41
  22. 2017Quaternion kinematics for the error-state Kalman filtercited by 30
  23. 2019gradSLAM: Automagically differentiable SLAMcited by 27
  24. 2024PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequencecited by 26
  25. 2023Quatro++: Robust Global Registration Exploiting Ground Segmentation for Loop Closing in LiDAR SLAMcited by 18
  26. 2022maplab 2.0 -- A Modular and Multi-Modal Mapping Frameworkcited by 14
  27. 2022DynaVINS: A Visual-Inertial SLAM for Dynamic Environmentscited by 11
  28. 2022Present and Future of SLAM in Extreme Underground Environmentscited by 9
  29. 2023SIM-Sync: From Certifiably Optimal Synchronization over the 3D Similarity Group to Scene Reconstruction with Learned Depthcited by 5
  30. 2024Kimera2: Robust and Accurate Metric-Semantic SLAM in the Real Worldcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 39; 2026: 91.

130 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  2. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  3. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  4. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  5. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 86
  6. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understandingcited by 55
  7. 2025Memory Forcing: Spatio-Temporal Memory for Consistent Scene Generation on Minecraftcited by 46
  8. 2026LoGeR: Long-Context Geometric Reconstruction with Hybrid Memorycited by 33
  9. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 32
  10. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
  11. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 25
  12. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
38 more
  1. 2026VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstructioncited by 22
  2. 2026VGGT-Omegacited by 20
  3. 2025Viser: Imperative, Web-based 3D Visualization in Pythoncited by 19
  4. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 18
  5. 2025Reasoning in Space via Grounding in the Worldcited by 18
  6. 2025OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformercited by 17
  7. 2026LongStream: Long-Sequence Streaming Autoregressive Visual Geometrycited by 17
  8. 2025PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Drivingcited by 16
  9. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  10. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 14
  11. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 13
  12. 2026pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoningcited by 12
  13. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matchingcited by 8
  14. 2025UniPR-3D: Towards Universal Visual Place Recognition with Visual Geometry Grounded Transformercited by 8
  15. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 8
  16. 2026World Reconstruction From Inconsistent Viewscited by 8
  17. 2026HorizonStream: Long-Horizon Attention for Streaming 3D Reconstructioncited by 8
  18. 2025SLAM-Former: Putting SLAM into One Transformercited by 7
  19. 2025E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Modelscited by 6
  20. 2025DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representationscited by 6
  21. 2026VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistencycited by 6
  22. 2026Stream3D: Sequential Multi-View 3D Generation via Evidential Memorycited by 6
  23. 2026Global Structure-from-Motion Meets Feedforward Reconstructioncited by 6
  24. 2025MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAMcited by 5
  25. 2025On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Modelscited by 5
  26. 2025LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstructioncited by 5
  27. 2025KV-Tracker: Real-Time Pose Tracking with Transformerscited by 5
  28. 2025LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mappingcited by 4
  29. 2025TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstructioncited by 4
  30. 2026Keyframe-Based Feed-Forward Visual Odometrycited by 3
  31. 2026S-MUSt3R: Sliding Multi-view 3D Reconstructioncited by 3
  32. 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimatescited by 3
  33. 2026SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenescited by 3
  34. 2026AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Visioncited by 3
  35. 2026Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memorycited by 3
  36. 2025ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environmentscited by 2
  37. 2025SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priorscited by 2
  38. 2025HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videoscited by 2

50 most cited of 130 All 130 (JSON)