mlsanityData to 14 Oct 2026

GTR: Gaussian Splatting Tracking and Reconstruction of Unknown Objects Based on Appearance and Geometric Complexity

arXiv 2505.11905 ↗First posted 17 May 2025cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

We present a novel method for 6-DoF object tracking and high-quality 3D reconstruction from monocular RGBD video. Existing methods, while achieving impressive results, often struggle with complex objects, particularly those exhibiting symmetry, intricate geometry or complex appearance. To bridge these gaps, we introduce an adaptive method that combines 3D Gaussian Splatting, hybrid geometry/appearance tracking, and key frame selection to achieve robust tracking and accurate reconstructions across a diverse range of objects. Additionally, we present a benchmark covering these challenging object classes, providing high-quality annotations for evaluating both tracking and reconstruction performance. Our approach demonstrates strong capabilities in recovering high-fidelity object meshes, setting a new standard for single-sensor 3D reconstruction in open-world environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 52 references that are in the map. First posted on arXiv 17 May 2025.

Builds on

48 of 52 references.

References · 48

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  6. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  7. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  8. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  9. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  10. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  11. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  12. 2023Gaussian Splatting SLAMcited by 415
36 more
  1. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  2. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
  3. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  4. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  5. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  6. 2021Learning Object-Compositional Neural Radiance Field for Editable Scene Renderingcited by 228
  7. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  8. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  9. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  10. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  11. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  12. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  13. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  14. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  15. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  16. 2024BootsTAP: Bootstrapped Training for Tracking-Any-Pointcited by 120
  17. 2020MeshSDF: Differentiable Iso-Surface Extractioncited by 112
  18. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  19. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  20. 2022Object-Compositional Neural Implicit Surfacescited by 74
  21. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 72
  22. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 70
  23. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  24. 2024FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descentcited by 61
  25. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  26. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 48
  27. 2016Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimationcited by 34
  28. 2023ZeroShape: Regression-based Zero-shot Shape Reconstructioncited by 30
  29. 2022PyPose: A Library for Robot Learning with Physics-based Optimizationcited by 29
  30. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 25
  31. 2020Dynamic SLAM: The Need For Speedcited by 24
  32. 2020Pix2Surf: Learning Parametric 3D Surface Models of Objects from Imagescited by 22
  33. 2023FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objectscited by 19
  34. 2021A Learned Stereo Depth System for Robotic Manipulation in Homescited by 14
  35. 2024Zero-Shot Multi-Object Scene Completioncited by 9
  36. 2023Fusing Visual Appearance and Geometry for Multi-modality 6DoF Object Trackingcited by 7

Built on by

Not cited yet.