mlsanityData to 14 Oct 2026

SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos

arXiv 2412.09401 ↗First posted 12 Dec 2024cs.CVcited by 102

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce SLAM3R, a novel and effective system for real-time, high-quality, dense 3D reconstruction using RGB videos. SLAM3R provides an end-to-end solution by seamlessly integrating local 3D reconstruction and global coordinate registration through feed-forward neural networks. Given an input video, the system first converts it into overlapping clips using a sliding window mechanism. Unlike traditional pose optimization-based methods, SLAM3R directly regresses 3D pointmaps from RGB images in each window and progressively aligns and deforms these local pointmaps to create a globally consistent scene reconstruction - all without explicitly solving any camera parameters. Experiments across datasets consistently show that SLAM3R achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS. Code available at: https://github.com/PKU-VCL-3DV/SLAM3R.

Key facts. Cited by 102 papers in the map (data through 14 Oct 2026). Builds on 59 of its 80 references that are in the map. First posted on arXiv 12 Dec 2024.

Builds on

59 of 80 references.

References · 59

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  6. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  8. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  9. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  10. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  11. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  12. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
38 more
  1. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  2. 2020Convolutional Occupancy Networkscited by 761
  3. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  4. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  7. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  8. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  9. 2016Direct Sparse Odometrycited by 485
  10. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  11. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  13. 2023Gaussian Splatting SLAMcited by 415
  14. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  15. 2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314
  16. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  17. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  18. 20243D Reconstruction with Spatial Memorycited by 277
  19. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  20. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  21. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  22. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  23. 2023NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAMcited by 164
  24. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  25. 2024High-quality Surface Reconstruction using Gaussian Surfelscited by 161
  26. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  27. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  28. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 152
  29. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 141
  30. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 133
  31. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  32. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 114
  33. 2024SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Modelcited by 96
  34. 2018DeepTAM: Deep Tracking and Mappingcited by 87
  35. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  36. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  37. 2020DI-Fusion: Online Implicit 3D Reconstruction with Deep Priorscited by 70
  38. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 46; 2026: 56.

102 papers.

Sort:

By area:

  1. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  2. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 170
  3. 2025GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Modelscited by 109
  4. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  5. 2025Easi3R: Estimating Disentangled Motion from DUSt3R Without Trainingcited by 91
  6. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 82
  7. 2025SpatialLM: Training Large Language Models for Structured Indoor Modelingcited by 65
  8. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  9. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 37
  10. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 35
  11. 2025WinT3R: Window-Based Streaming Reconstruction with Camera Token Poolcited by 35
  12. 2025What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Modelscited by 29
38 more
  1. 2025VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstructioncited by 28
  2. 2026VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstructioncited by 28
  3. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  4. 2026LongStream: Long-Sequence Streaming Autoregressive Visual Geometrycited by 23
  5. 2025Test3R: Learning to Reconstruct 3D at Test Timecited by 20
  6. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 20
  7. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  8. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 18
  9. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 16
  10. 2025Rig3R: Rig-Aware Conditioning for Learned 3D Reconstructioncited by 11
  11. 2025Can Video Diffusion Model Reconstruct 4D Geometry?cited by 10
  12. 2025Review of Feed-forward 3D Reconstruction: From DUSt3R to VGGTcited by 10
  13. 2025Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videoscited by 10
  14. 20254D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimationcited by 10
  15. 2025SLAM-Former: Putting SLAM into One Transformercited by 9
  16. 2026SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigationcited by 9
  17. 2025Unposed 3DGS Reconstruction with Probabilistic Procrustes Mappingcited by 8
  18. 2025PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstructioncited by 8
  19. 2025CUPID: Generative 3D Reconstruction via Joint Object and Pose Modelingcited by 8
  20. 2025E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Modelscited by 7
  21. 2025MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splattingcited by 7
  22. 2026Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyondcited by 7
  23. 2026Stream3D: Sequential Multi-View 3D Generation via Evidential Memorycited by 7
  24. 2025DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representationscited by 6
  25. 2025MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAMcited by 6
  26. 2025GRS-SLAM3R: Real-Time Dense SLAM with Gated Recurrent Statecited by 6
  27. 2025Analyzing the Mechanism of Attention Collapse in VGGT from a Dynamics Perspectivecited by 6
  28. 2025Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstructioncited by 5
  29. 2025LiDAR-VGGT: Cross-Modal Coarse-to-Fine Fusion for Globally Consistent and Metric-Scale Dense Mappingcited by 5
  30. 2025TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstructioncited by 5
  31. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  32. 2025MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priorscited by 4
  33. 2026FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentationcited by 4
  34. 2025Mem4D: Decoupling Static and Dynamic Memory for Dynamic Scene Reconstructioncited by 3
  35. 2025EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenescited by 3
  36. 2025EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Flycited by 3
  37. 2026Marginalized Bundle Adjustment: Multi-View Camera Pose from Monocular Depth Estimatescited by 3
  38. 2026FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometrycited by 3

50 most cited of 102 All 102 (JSON)