mlsanityData to 14 Oct 2026

6DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splatting

arXiv 2412.01543 ↗First posted 2 Dec 2024cs.CV cs.ROcited by 11

Not on the map. Why?

Abstract (arXiv)

Efficient and accurate object pose estimation is an essential component for modern vision systems in many applications such as Augmented Reality, autonomous driving, and robotics. While research in model-based 6D object pose estimation has delivered promising results, model-free methods are hindered by the high computational load in rendering and inferring consistent poses of arbitrary objects in a live RGB-D video stream. To address this issue, we present 6DOPE-GS, a novel method for online 6D object pose estimation & tracking with a single RGB-D camera by effectively leveraging advances in Gaussian Splatting. Thanks to the fast differentiable rendering capabilities of Gaussian Splatting, 6DOPE-GS can simultaneously optimize for 6D object poses and 3D object reconstruction. To achieve the necessary efficiency and accuracy for live tracking, our method uses incremental 2D Gaussian Splatting with an intelligent dynamic keyframe selection procedure to achieve high spatial object coverage and prevent erroneous pose updates. We also propose an opacity statistic-based pruning mechanism for adaptive Gaussian density control, to ensure training stability and efficiency. We evaluate our method on the HO3D and YCBInEOAT datasets and show that 6DOPE-GS matches the performance of state-of-the-art baselines for model-free simultaneous 6D pose tracking and reconstruction while providing a 5× speedup. We also demonstrate the method's suitability for live, dynamic object tracking and reconstruction in a real-world setting.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 61 of its 85 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

61 of 85 references.

References · 61

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  5. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  6. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  7. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  8. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 737
  9. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  10. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  11. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  12. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
38 more
  1. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  2. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  3. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 436
  4. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  5. 2023Gaussian Splatting SLAMcited by 415
  6. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  7. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  8. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  9. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  10. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  11. 20243D Reconstruction with Spatial Memorycited by 277
  12. 2020Neural Unsigned Distance Fields for Implicit Function Learningcited by 265
  13. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  14. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  15. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  16. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  17. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  18. 2017A Survey of Structure from Motioncited by 158
  19. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  20. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  21. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  22. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  23. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 139
  24. 2024Revising Densification in Gaussian Splattingcited by 128
  25. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  26. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  27. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  28. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  29. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  30. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  31. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 101
  32. 2018MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objectscited by 95
  33. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  34. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 90
  35. 20176-DoF Object Pose from Semantic Keypointscited by 89
  36. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  37. 2019Single-Stage 6D Object Pose Estimationcited by 88
  38. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 10.

11 papers.

  1. 2025Light Field Based 6DoF Tracking of Previously Unobserved Objectscited by 1
  2. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  3. 2026Point2Pose: Occlusion-Recovering 6D Pose Tracking and 3D Reconstruction for Multiple Unknown Objects Via 2D Point Trackerscited by 1
  4. 2026SpectralSplats: Robust Differentiable Tracking via Spectral Moment Supervisioncited by 0
  5. 2026Detailed Geometry and Appearance from Opportunistic Motioncited by 0
  6. 2026Paparazzo: Active Mapping of Moving 3D Objectscited by 0
  7. 2026Pose Anything Anywhere:Model-free Object Poses from Arbitrary Referencescited by 0
  8. 2026Dynamic Inverse Rendering for Enhanced Material-Lighting Decompositioncited by 0
  9. 2026LEGAU: Learning Semantic Gaussian Priors for Scalable Category-level Pose Estimationcited by 0
  10. 2026GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose Trackingcited by 0
  11. 2026NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinementcited by 0