mlsanityData to 7 Oct 2026

MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

arXiv 2412.12392 ↗First posted 16 Dec 2024cs.CV cs.ROcited by 198

Not on the map. Why?

Abstract (arXiv)

We present a real-time monocular dense SLAM system designed bottom-up from MASt3R, a two-view 3D reconstruction and matching prior. Equipped with this strong prior, our system is robust on in-the-wild video sequences despite making no assumption on a fixed or parametric camera model beyond a unique camera centre. We introduce efficient methods for pointmap matching, camera tracking and local fusion, graph construction and loop closure, and second-order global optimisation. With known calibration, a simple modification to the system achieves state-of-the-art performance across various benchmarks. Altogether, we propose a plug-and-play monocular SLAM system capable of producing globally-consistent poses and dense geometry while operating at 15 FPS.

Key facts. Cited by 198 papers in the map (data through 7 Oct 2026). Builds on 40 of its 58 references that are in the map. First posted on arXiv 16 Dec 2024.

Builds on

40 of 58 references.

References · 40

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  4. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  5. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  8. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  9. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  10. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  11. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  12. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
28 more
  1. 2023Gaussian Splatting SLAMcited by 410
  2. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  3. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  4. 20243D Reconstruction with Spatial Memorycited by 269
  5. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  6. 2024Global Structure-from-Motion Revisitedcited by 215
  7. 2020Atlas: End-to-End 3D Scene Reconstruction from Posed Imagescited by 206
  8. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  9. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  10. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 162
  11. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  12. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  13. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  14. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 122
  15. 2018A micro Lie theory for state estimation in roboticscited by 117
  16. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  17. 2018DeepTAM: Deep Tracking and Mappingcited by 87
  18. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  19. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  20. 2024Deep Patch Visual SLAMcited by 68
  21. 2014Designing Deep Networks for Surface Normal Estimationcited by 59
  22. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 54
  23. 2019Why Having 10,000 Parameters in Your Camera Model is Better Than Twelvecited by 43
  24. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  25. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  26. 2023Learning a Depth Covariance Functioncited by 16
  27. 2023SuperPrimitive: Scene Reconstruction at a Primitive Levelcited by 11
  28. 2024COMO: Compact Mapping and Odometrycited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 84; 2026: 114.

198 papers.

Sort:

By area:

  1. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  2. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  3. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  4. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  5. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 154
  6. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  7. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  8. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  9. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 88
  10. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  11. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  12. 2025SpatialLM: Training Large Language Models for Structured Indoor Modelingcited by 63
38 more
  1. 20254DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videoscited by 46
  2. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  3. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 44
  4. 2025UFM: A Simple Path towards Unified Dense Correspondence with Flowcited by 35
  5. 2025WinT3R: Window-Based Streaming Reconstruction with Camera Token Poolcited by 32
  6. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 32
  7. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 31
  8. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
  9. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  10. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 25
  11. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  12. 2026VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstructioncited by 22
  13. 2025Outdoor Monocular SLAM with Global Scale-Consistent 3D Gaussian Pointmapscited by 21
  14. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 18
  15. 2025Articulated Object Estimation in the Wildcited by 18
  16. 2025AnyCalib: On-Manifold Learning for Model-Agnostic Single-View Camera Calibrationcited by 17
  17. 2026LongStream: Long-Sequence Streaming Autoregressive Visual Geometrycited by 17
  18. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  19. 2025LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Mergingcited by 16
  20. 2025FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolutioncited by 14
  21. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  22. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 13
  23. 2025Learning to Drive Anywhere with Model-Based Reannotationcited by 12
  24. 2025Benchmarking Egocentric Visual-Inertial SLAM at City Scalecited by 12
  25. 2025Rig3R: Rig-Aware Conditioning for Learned 3D Reconstructioncited by 11
  26. 2025RynnEC: Bringing MLLMs into Embodied Worldcited by 11
  27. 2025Can Video Diffusion Model Reconstruct 4D Geometry?cited by 10
  28. 2025The Coralscapes Dataset: Semantic Scene Understanding in Coral Reefscited by 9
  29. 2025Learning 3D-Gaussian Simulators from RGB Videoscited by 8
  30. 2025Understanding Multi-View Transformerscited by 8
  31. 2025UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstructioncited by 8
  32. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 8
  33. 2026MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentationcited by 8
  34. 2026HorizonStream: Long-Horizon Attention for Streaming 3D Reconstructioncited by 8
  35. 2025SLAM-Former: Putting SLAM into One Transformercited by 7
  36. 2025E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Modelscited by 6
  37. 2025DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representationscited by 6
  38. 2025GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent Statecited by 6

50 most cited of 198 All 198 (JSON)