mlsanityData to 7 Oct 2026

iSLAM: Imperative SLAM

arXiv 2306.07894 ↗First posted 13 Jun 2023cs.RO cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Simultaneous Localization and Mapping (SLAM) stands as one of the critical challenges in robot navigation. A SLAM system often consists of a front-end component for motion estimation and a back-end system for eliminating estimation drifts. Recent advancements suggest that data-driven methods are highly effective for front-end tasks, while geometry-based methods continue to be essential in the back-end processes. However, such a decoupled paradigm between the data-driven front-end and geometry-based back-end can lead to sub-optimal performance, consequently reducing the system's capabilities and generalization potential. To solve this problem, we proposed a novel self-supervised imperative learning framework, named imperative SLAM (iSLAM), which fosters reciprocal correction between the front-end and back-end, thus enhancing performance without necessitating any external supervision. Specifically, we formulate the SLAM problem as a bilevel optimization so that the front-end and back-end are bidirectionally connected. As a result, the front-end model can learn global geometric knowledge obtained through pose graph optimization by back-propagating the residuals from the back-end component. We showcase the effectiveness of this new framework through an application of stereo-inertial SLAM. The experiments show that the iSLAM training strategy achieves an accuracy improvement of 22% on average over a baseline model. To the best of our knowledge, iSLAM is the first SLAM system showing that the front-end and back-end components can mutually correct each other in a self-supervised manner.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 40 of its 68 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

40 of 68 references.

References · 40

  1. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  2. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  3. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  4. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  6. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  7. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  8. 2016Direct Sparse Odometrycited by 479
  9. 2017VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimatorcited by 418
  10. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  11. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  12. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
28 more
  1. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 219
  2. 2016DeMoN: Depth and Motion Network for Learning Monocular Stereocited by 200
  3. 2022Deep Patch Visual Odometrycited by 186
  4. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  5. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  6. 2018BA-Net: Dense Bundle Adjustment Networkcited by 173
  7. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  8. 2018CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAMcited by 151
  9. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  10. 2020A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Criticcited by 141
  11. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  12. 2020TartanVO: A Generalizable Learning-based VOcited by 107
  13. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  14. 2018StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Predictioncited by 88
  15. 2017Camera Relocalization by Computing Pairwise Relative Poses Using Convolutional Neural Networkcited by 79
  16. 2019Deep Declarative Networks: A New Hopecited by 77
  17. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 62
  18. 2023iPlanner: Imperative Path Planningcited by 32
  19. 2022PyPose: A Library for Robot Learning with Physics-based Optimizationcited by 29
  20. 2022DiffPoseNet: Direct Differentiable Camera Pose Estimationcited by 27
  21. 2019DeepVIO: Self-supervised Deep Learning of Monocular Visual Inertial Odometry using 3D Geometric Constraintscited by 26
  22. 2021A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphscited by 26
  23. 2022Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selectioncited by 17
  24. 2020TP-TIO: A Robust Thermal-Inertial Odometry with Deep ThermalPointcited by 11
  25. 2021AirLoop: Lifelong Loop Closure Detectioncited by 11
  26. 2022AirVO: An Illumination-Robust Point-Line Visual Odometrycited by 9
  27. 2017A Bridge Between Hyperparameter Optimization and Learning-to-learncited by 6
  28. 2021Learning Generalized Visual Odometry Using Position-Aware Optical Flow and Geometric Bundle Adjustmentcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 5; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024Deep Patch Visual SLAMcited by 68
  2. 2024MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometrycited by 19
  3. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
  4. 2025VINGS-Mono: Visual-Inertial Gaussian Splatting Monocular SLAM in Large Scenescited by 11
  5. 2024Bundle Adjustment in the Eager Modecited by 6
  6. 2025DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Modelcited by 5
  7. 2024iMTSP: Solving Min-Max Multiple Traveling Salesman Problem with Imperative Learningcited by 4
  8. 2024Salient Sparse Visual Odometry With Pose-Only Supervisioncited by 2
  9. 2025BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Modulecited by 1
  10. 2025An Online Adaptation Method for Robust Depth Estimation and Visual Odometry in the Open Worldcited by 1
  11. 2025Monocular Visual Odometry without Calibration or Test-time Optimizationcited by 0
  12. 2026Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraintscited by 0
2 more
  1. 2026NSFlow: End-to-End Differentiable Neuro-Symbolic Optical Flow for Visual Odometrycited by 0
  2. 2026Valerant: An Automatic Navigable Game Map Generator via Action-Conditioned World Model Explorationcited by 0