mlsanityData to 14 Oct 2026

VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction

arXiv 2601.19887 ↗First posted 27 Jan 2026cs.CV cs.ROcited by 28

Not on the map. Why?

Abstract (arXiv)

We present VGGT-SLAM 2.0, a real-time RGB feed-forward SLAM system which substantially improves upon VGGT-SLAM for incrementally aligning submaps created from VGGT. Firstly, we remove high-dimensional 15-degree-of-freedom drift and planar degeneracy from VGGT-SLAM by creating a new factor graph design while still addressing the reconstruction ambiguity of VGGT given unknown camera intrinsics. Secondly, by studying the attention layers of VGGT, we show that one of the layers is well suited to assist in image retrieval verification for free without additional training, which enables both rejecting false positive matches and allows for completing more loop closures. Finally, we conduct a suite of experiments which includes showing VGGT-SLAM 2.0 can easily be adapted for open-set object detection and demonstrating real-time performance while running online onboard a ground robot using a Jetson Thor. We test in environments ranging from cluttered indoor apartments and office scenes to a 4,200 square foot barn, and we also demonstrate VGGT-SLAM 2.0 achieves the highest accuracy on the TUM dataset with about 23 percent less pose error than VGGT-SLAM. Code will be released upon publication.

Key facts. Cited by 28 papers in the map (data through 14 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

42 of 55 references.

References · 42

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  5. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  6. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  7. 2025SAM 3: Segment Anything with Conceptscited by 906
  8. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  9. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  10. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  11. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  12. 2025Continuous 3D Perception Model with Persistent Statecited by 548
30 more
  1. 2016Direct Sparse Odometrycited by 485
  2. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 423
  3. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  4. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  5. 20243D Reconstruction with Spatial Memorycited by 277
  6. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 228
  7. 2024Global Structure-from-Motion Revisitedcited by 218
  8. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  9. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  10. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  11. 2023Optimal Transport Aggregation for Visual Place Recognitioncited by 152
  12. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  13. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 133
  14. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 129
  15. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  16. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 115
  17. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102
  18. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 100
  19. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 91
  20. 2024Clio: Real-time Task-Driven Open-Set 3D Scene Graphscited by 81
  21. 2024Deep Patch Visual SLAMcited by 71
  22. 2024PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequencecited by 28
  23. 2025Emergent Outlier View Rejection in Visual Geometry Grounded Transformerscited by 22
  24. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 16
  25. 2017Efficient Decentralized Visual Place Recognition From Full-Image Descriptorscited by 8
  26. 2025Understanding Multi-View Transformerscited by 8
  27. 2025On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Modelscited by 7
  28. 2025MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAMcited by 6
  29. 2025TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstructioncited by 5
  30. 2025SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priorscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 28.

28 papers.

Sort:

By area:

  1. 2026Glob3R: Global Structure-from-Motion with 3D Foundation Modelscited by 4
  2. 2026M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAMcited by 2
  3. 2026Ray-Aware Pointer Memory with Adaptive Updates for Streaming 3D Reconstructioncited by 1
  4. 2026LEXI-SG: Monocular 3D Scene Graph Mapping with Room-Guided Feed-Forward Reconstructioncited by 1
  5. 2026Compressing History into Memory: Distilling Transformers into Recurrent Transformerscited by 1
  6. 2026Why does Deep Learning Improve Visual SLAM?cited by 1
  7. 2026Look Up and Look Back: Hidden Attention and Latent Orientation in a Frozen Foundation Model for Panoramic SLAMcited by 1
  8. 2026GeoFF3D: Coordinate-Anchored Feed-Forward Reconstruction for Large-Scale UAV Mappingcited by 1
  9. 2026RIGOR: Rig-Informed Geometry for Omnidirectional Reconstructioncited by 1
  10. 2026Online Adaptation of Visual Odometry Frontends with Image-Conditioned Reinforcement Learningcited by 0
  11. 2026Accelerating Transformer-Based Monocular SLAM via Geometric Utility Scoringcited by 0
  12. 2026SpatialBench: Is Your Spatial Foundation Model an All-Round Player?cited by 0
16 more
  1. 2026PixelLoop: Shortcut Topological Navigation with Pixel-Level Loopscited by 0
  2. 2026GeoWeaver: Accurate Long-Sequence 3D Reconstruction via Hierarchical Geometric Assemblycited by 0
  3. 2026AquaFlow: A Monocular Gaussian Splatting SLAM for Underwater Streaming Reconstructioncited by 0
  4. 2026Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstructioncited by 0
  5. 2026FFVO: A Feedforward Pose Decoder for Long-Horizon Visual Odometrycited by 0
  6. 2026SURE-Map: Self-Correcting Streaming Geometric Foundation Modelscited by 0
  7. 2026AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backendcited by 0
  8. 2026VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priorscited by 0
  9. 2026DAVIO: Dense Monocular-Inertial SLAM with Feed-Forward Initialization and Pose-Conditioned Mappingcited by 0
  10. 2026Matisse: Evidence-Space Reasoning for Active 3D Reconstructioncited by 0
  11. 2026CLoSeR: Closing the Loop for Long-Context Streaming Reconstructioncited by 0
  12. 2026F2 SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAMcited by 0
  13. 2026VOMMI: Collecting and Leveraging Portable Demonstrations for Mobile Manipulationcited by 0
  14. 2026MIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward Visioncited by 0
  15. 2026Dense Endoluminal Mapping and Localisation from Monocular Bronchoscopycited by 0
  16. 2026Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometrycited by 0