mlsanityData to 7 Oct 2026

D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidance

arXiv 2207.08794 ↗First posted 18 Jul 2022cs.CV cs.ROcited by 9

Not on the map. Why?

Abstract (arXiv)

In this paper, we introduce a self-supervised deep SLAM method that robustly operates in dynamic scenes while accurately identifying dynamic components. Our method leverages a dual-flow representation for static flow and dynamic flow, facilitating effective scene decomposition in dynamic environments. We propose a dynamic update module based on this representation and develop a dense SLAM system that excels in dynamic scenarios. In addition, we design a self-supervised training scheme using DINO as a prior, enabling label-free training. Our method achieves superior accuracy compared to other self-supervised methods. It also matches or even surpasses the performance of existing supervised methods in some cases. All code and data will be made publicly available upon acceptance.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 57 of its 104 references that are in the map. First posted on arXiv 18 Jul 2022.

Builds on

57 of 104 references.

References · 57

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2017Mask R-CNNcited by 7,259
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  6. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  7. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  8. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  9. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  10. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  11. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  12. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
38 more
  1. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  2. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  3. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  4. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  5. 2016Direct Sparse Odometrycited by 479
  6. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  7. 2020Virtual KITTI 2cited by 345
  8. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  9. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 241
  10. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  11. 2020A survey of loss functions for semantic segmentationcited by 216
  12. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  13. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  14. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  15. 2017Geometry-Aware Learning of Maps for Camera Localizationcited by 161
  16. 2017CNN-SLAM: Real-time dense monocular SLAM with learned depth predictioncited by 152
  17. 2018DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenescited by 130
  18. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  19. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 108
  20. 2020TartanVO: A Generalizable Learning-based VOcited by 107
  21. 2018CubeSLAM: Monocular 3D Object SLAMcited by 101
  22. 2018The TUM VI Benchmark for Evaluating Visual-Inertial Odometrycited by 94
  23. 2018DS-SLAM: A Semantic Visual SLAM towards Dynamic Environmentscited by 90
  24. 2018DeepTAM: Deep Tracking and Mappingcited by 87
  25. 2020UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learningcited by 49
  26. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  27. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  28. 2018Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimationcited by 38
  29. 2020FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flowcited by 36
  30. 2019EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Associationcited by 28
  31. 2019Mono-SF: Multi-View Geometry Meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenescited by 27
  32. 2018Online Temporal Calibration for Monocular Visual-Inertial Systemscited by 26
  33. 2022PVO: Panoptic Visual Odometrycited by 26
  34. 2019Direct Sparse Mappingcited by 25
  35. 2020Dynamic SLAM: The Need For Speedcited by 24
  36. 2020EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentationcited by 22
  37. 2021DF-VO: What Should Be Learnt for Visual Odometry?cited by 22
  38. 2021LIFT-SLAM: a deep-learning feature-based monocular visual SLAM methodcited by 20

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 5; 2025: 3.

9 papers.

  1. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  2. 2024Deep Patch Visual SLAMcited by 68
  3. 2022iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Trackingcited by 22
  4. 2024DynaSurfGS: Dynamic Surface Reconstruction with Planar-based Gaussian Splattingcited by 19
  5. 2024RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenescited by 14
  6. 2025DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representationscited by 6
  7. 2024Salient Sparse Visual Odometry With Pose-Only Supervisioncited by 2
  8. 2025ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videoscited by 1
  9. 2025Dropping the D: RGB-D SLAM Without the Depth Sensorcited by 0