mlsanityData to 14 Oct 2026

SLAM-Former: Putting SLAM into One Transformer

arXiv 2509.16909 ↗First posted 21 Sep 2025cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

We present SLAM-Former, a neural approach that integrates full SLAM capabilities into a single transformer. Similar to traditional SLAM systems, SLAM-Former comprises both a frontend and a back-end that operate in tandem. The frontend processes sequential monocular images in real-time for incremental mapping and tracking, while the backend performs global refinement to ensure a geometrically consistent result. This alternating execution allows the frontend and back-end to mutually promote one another, enhancing overall system performance. Comprehensive experimental results demonstrate that SLAM- Former achieves superior or highly competitive performance compared to state-of-the-art dense SLAM methods.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 38 of its 47 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

38 of 47 references.

References · 38

  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. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  5. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  6. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  7. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  8. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  9. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  10. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
26 more
  1. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  2. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  3. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  4. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  5. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  6. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  7. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  8. 20243D Reconstruction with Spatial Memorycited by 277
  9. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 205
  10. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  11. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  12. 2025DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Modelscited by 181
  13. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
  14. 2025Streaming 4D Visual Geometry Transformercited by 161
  15. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 152
  16. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 136
  17. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 133
  18. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  19. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102
  20. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 82
  21. 2024Deep Patch Visual SLAMcited by 71
  22. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  23. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  24. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  25. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 16
  26. 2024SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modelingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 8.

9 papers.

  1. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  2. 2026Efficient Feature-Free Initialization for Monocular Visual-Inertial Systems Using a Feed-Forward 3D Modelcited by 1
  3. 2026SLAMFormer-∞: Infinite SLAM Transformer for Unbounded Frontend and Backend Processingcited by 1
  4. 2026BA-T: An Iterative Transformer for Two-View Bundle Adjustmentcited by 0
  5. 2026Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstructioncited by 0
  6. 2026AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backendcited by 0
  7. 2026World SLAM Model: Joint World Modeling for SLAM and Navigationcited by 0
  8. 2026F2 SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAMcited by 0
  9. 2026Remember, Revisit, Revise: Scaffold Memory for Long-Horizon 3D Geometrycited by 0