mlsanityData to 7 Oct 2026

ReFusion: 3D Reconstruction in Dynamic Environments for RGB-D Cameras Exploiting Residuals

arXiv 1905.02082 ↗First posted 6 May 2019cs.ROcited by 180

Not on the map. Why?

Abstract (arXiv)

Mapping and localization are essential capabilities of robotic systems. Although the majority of mapping systems focus on static environments, the deployment in real-world situations requires them to handle dynamic objects. In this paper, we propose an approach for an RGB-D sensor that is able to consistently map scenes containing multiple dynamic elements. For localization and mapping, we employ an efficient direct tracking on the truncated signed distance function (TSDF) and leverage color information encoded in the TSDF to estimate the pose of the sensor. The TSDF is efficiently represented using voxel hashing, with most computations parallelized on a GPU. For detecting dynamics, we exploit the residuals obtained after an initial registration, together with the explicit modeling of free space in the model. We evaluate our approach on existing datasets, and provide a new dataset showing highly dynamic scenes. These experiments show that our approach often surpass other state-of-the-art dense SLAM methods. We make available our dataset with the ground truth for both the trajectory of the RGB-D sensor obtained by a motion capture system and the model of the static environment using a high-precision terrestrial laser scanner. Finally, we release our approach as open source code.

Key facts. Cited by 180 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 4; 2024: 17; 2025: 62; 2026: 89.

180 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  3. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  4. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  5. 2024DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videoscited by 202
  6. 2025Video Depth Anything: Consistent Depth Estimation for Super-Long Videoscited by 202
  7. 2025Streaming 4D Visual Geometry Transformercited by 147
  8. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  9. 2025Aether: Geometric-Aware Unified World Modelingcited by 94
  10. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  11. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 84
  12. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
38 more
  1. 2024Align3R: Aligned Monocular Depth Estimation for Dynamic Videoscited by 79
  2. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 76
  3. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  4. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  5. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 62
  6. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 59
  7. 2026InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streamscited by 51
  8. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  9. 2025WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environmentscited by 48
  10. 2025Efficiently Reconstructing Dynamic Scenes One D4RT at a Timecited by 46
  11. 2022SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representationscited by 44
  12. 2025Human3R: Everyone Everywhere All at Oncecited by 35
  13. 2026LoGeR: Long-Context Geometric Reconstruction with Hybrid Memorycited by 33
  14. 2025Any4D: Unified Feed-Forward Metric 4D Reconstructioncited by 32
  15. 2026V-DPM: 4D Video Reconstruction with Dynamic Point Mapscited by 29
  16. 2024Video Depth without Video Modelscited by 28
  17. 2025Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Videocited by 27
  18. 2025POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstructioncited by 24
  19. 2025Back on Track: Bundle Adjustment for Dynamic Scene Reconstructioncited by 23
  20. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 23
  21. 2026ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Trainingcited by 23
  22. 2024DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAMcited by 22
  23. 2025MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Expertscited by 19
  24. 2025Articulated Object Estimation in the Wildcited by 18
  25. 20264RC: 4D Reconstruction via Conditional Querying Anytime and Anywherecited by 17
  26. 2023DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fieldscited by 16
  27. 2025DeGauss: Dynamic-Static Decomposition with Gaussian Splatting for Distractor-free 3D Reconstructioncited by 16
  28. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  29. 2025FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attentioncited by 15
  30. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 14
  31. 2024PG-SLAM: Photo-realistic and Geometry-aware RGB-D SLAM in Dynamic Environmentscited by 11
  32. 2024Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priorscited by 11
  33. 2025VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenescited by 11
  34. 2025G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integrationcited by 11
  35. 2021ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Descriptioncited by 10
  36. 2025DynaGSLAM: Real-Time Gaussian-Splatting SLAM for Online Rendering, Tracking, Motion Predictions of Moving Objects in Dynamic Scenescited by 10
  37. 20254D Gaussian Splatting SLAMcited by 10
  38. 2025D2USt3R: Enhancing 3D Reconstruction for Dynamic Scenescited by 10

50 most cited of 180 All 180 (JSON)