mlsanityData to 14 Oct 2026

NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinement

arXiv 2610.13309 ↗First posted 9 Oct 2026cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch during onboarding and have long trailed their model-based counterparts. We present NovaSplat, a model-free pipeline that closes this gap. From a short smartphone video captured at onboarding, we train a 3D Gaussian Splatting (3DGS) model that serves both as a template source for detection and coarse pose estimation and as a differentiable backbone for pose refinement. Our refiner optimizes the object-to-camera pose with combined photometric and geometric losses under a continuous rotation parametrization free of gradient singularities. On a household-object benchmark, NovaSplat surpasses all model-based methods. On a challenging industrial benchmark with textureless and specular surfaces, it outperforms all model-free competitors while substantially narrowing the gap to model-based ones. We further introduce NovaSplat-Lite, an inference variant that is 3.1× faster at negligible accuracy cost. Code will be made available at hrefhttps://github.com/POSE-Lab/novasplathttps://github.com/POSE-Lab/novasplat.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 40 of its 55 references that are in the map. First posted on arXiv 9 Oct 2026.

Builds on

40 of 55 references.

References · 40

  1. 2023Segment Anythingcited by 8,234
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  5. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  7. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  8. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  9. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  10. 2024Global Structure-from-Motion Revisitedcited by 218
  11. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  12. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 166
28 more
  1. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  2. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  3. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  4. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  5. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  6. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  7. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  8. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  9. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 90
  10. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  11. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 87
  12. 20226-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmarkcited by 86
  13. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 58
  14. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  15. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 49
  16. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 42
  17. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 33
  18. 2025MeshSplatting: Differentiable Rendering with Opaque Meshescited by 20
  19. 2025BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimationcited by 19
  20. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 18
  21. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 15
  22. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 14
  23. 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 11
  24. 2024GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splattingcited by 3
  25. 2026IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and toolscited by 2
  26. 2025OPFormer: Object Pose Estimation leveraging foundation model with geometric encodingcited by 1
  27. 2025WALDO: Where Unseen Model-based 6D Pose Estimation Meets Occlusioncited by 1
  28. 2026Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perceptioncited by 1

Built on by

Not cited yet.