mlsanityData to 14 Oct 2026

GelSLAM: A Real-time, High-Fidelity, and Robust 3D Tactile SLAM System

arXiv 2508.15990 ↗First posted 21 Aug 2025cs.RO cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Accurately perceiving an object's pose and shape is essential for precise grasping and manipulation. Compared to common vision-based methods, tactile sensing offers advantages in precision and immunity to occlusion when tracking and reconstructing objects in contact. This makes it particularly valuable for in-hand and other high-precision manipulation tasks. In this work, we present GelSLAM, a real-time 3D SLAM system that relies solely on tactile sensing to estimate object pose over long periods and reconstruct object shapes with high fidelity. Unlike traditional point cloud-based approaches, GelSLAM uses tactile-derived surface normals and curvatures for robust tracking and loop closure. It can track object motion in real time with low error and minimal drift, and reconstruct shapes with submillimeter accuracy, even for low-texture objects such as wooden tools. GelSLAM extends tactile sensing beyond local contact to enable global, long-horizon spatial perception, and we believe it will serve as a foundation for many precise manipulation tasks involving interaction with objects in hand. The video demo, code, and dataset are available at https://joehjhuang.github.io/gelslam.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 64 references that are in the map. First posted on arXiv 21 Aug 2025.

Builds on

39 of 64 references.

References · 39

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  3. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  4. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  5. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  6. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
  7. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  10. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  11. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  12. 2022Robot Operating System 2: Design, Architecture, and Uses In The Wildcited by 199
27 more
  1. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 167
  2. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  3. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  4. 2019Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejectioncited by 94
  5. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  6. 2018FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterizationcited by 43
  7. 20203D Shape Reconstruction from Vision and Touchcited by 42
  8. 2021GelSlim3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Fingercited by 41
  9. 2021GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Fingercited by 34
  10. 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
  11. 2022MidasTouch: Monte-Carlo inference over distributions across sliding touchcited by 33
  12. 20183D Shape Perception from Monocular Vision, Touch, and Shape Priorscited by 31
  13. 2021ShapeMap 3-D: Efficient shape mapping through dense touch and visioncited by 31
  14. 2019Tactile Mapping and Localization from High-Resolution Tactile Imprintscited by 19
  15. 2020Tactile SLAM: Real-time inference of shape and pose from planar pushingcited by 15
  16. 2022Tac2Pose: Tactile Object Pose Estimation from the First Touchcited by 15
  17. 2023TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensingcited by 15
  18. 2023Visual-Tactile Sensing for In-Hand Object Reconstructioncited by 13
  19. 2023FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedbackcited by 12
  20. 2024Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfacescited by 12
  21. 2022Active Visuo-Haptic Object Shape Completioncited by 11
  22. 2021PatchGraph: In-hand tactile tracking with learned surface normalscited by 10
  23. 2022Active Visuo-Tactile Interactive Robotic Perception for Accurate Object Pose Estimation in Dense Cluttercited by 7
  24. 2024NormalFlow: Fast, Robust, and Accurate Contact-based Object 6DoF Pose Tracking with Vision-based Tactile Sensorscited by 5
  25. 2025V-HOP: Visuo-Haptic 6D Object Pose Trackingcited by 5
  26. 2022Tac2Structure: Object Surface Reconstruction Only through Multi Times Touchcited by 4
  27. 2025GelBelt: A Vision-based Tactile Sensor for Continuous Sensing of Large Surfacescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learningcited by 3
  2. 2026NLiPsCalib: An Efficient Calibration Framework for High-Fidelity 3D Reconstruction of Curved Visuotactile Sensorscited by 2
  3. 2026TouchAnything: Diffusion-Guided 3D Reconstruction from Sparse Robot Touchescited by 1
  4. 2026VisTa3D: A Dataset and Benchmark for Thin Object Reconstruction from Vision, Tactile, and 3D Point Cloudscited by 1
  5. 2026VTLoc: Learning-based Tactile Contact Localization in Visual Point Cloudscited by 0
  6. 2026Calibration-Free Surface Normals Estimation in Vision-Based Tactile Sensing using Universal Photometric Stereocited by 0