mlsanityData to 14 Oct 2026

SCOPE: Semantic Conditioning for Sim2Real Category-Level Object Pose Estimation in Robotics

arXiv 2509.24572 ↗First posted 29 Sep 2025cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Object manipulation requires accurate object pose estimation. In open environments, robots encounter unknown objects, which requires semantic understanding in order to generalize both to known categories and beyond. To resolve this challenge, we present SCOPE, a diffusion-based category-level object pose estimation model that eliminates the need for discrete category labels by leveraging DINOv2 features as continuous semantic priors. By combining these DINOv2 features with photorealistic training data and a noise model for point normals, we reduce the Sim2Real gap in category-level object pose estimation. Furthermore, injecting the continuous semantic priors via cross-attention enables SCOPE to learn canonicalized object coordinate systems across object instances beyond the distribution of known categories. SCOPE outperforms the current state of the art in synthetically trained category-level object pose estimation, achieving a relative improvement of 31.9% on the 5^circ5cm metric. Additional experiments on two instance-level datasets demonstrate generalization beyond known object categories, enabling grasping of unseen objects from unknown categories with a success rate of up to 100%. Code available: https://github.com/hoenigpeter/scope.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 61 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

47 of 61 references.

References · 47

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  6. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  7. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  8. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  11. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  12. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
35 more
  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  2. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  3. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  4. 2020TEASER: Fast and Certifiable Point Cloud Registrationcited by 274
  5. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  6. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  7. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  8. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  9. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  10. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  11. 2019BlenderProccited by 77
  12. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  13. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 72
  14. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusioncited by 72
  15. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 70
  16. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  17. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  18. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 50
  19. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  20. 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
  21. 2023D3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangementcited by 35
  22. 20206D Object Pose Regression via Supervised Learning on Point Cloudscited by 33
  23. 2022CPPF: Towards Robust Category-Level 9D Pose Estimation in the Wildcited by 28
  24. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 25
  25. 2024OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objectscited by 22
  26. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  27. 2020A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimatorscited by 18
  28. 2024CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledgecited by 16
  29. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  30. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  31. 2022Sim2Real Instance-Level Style Transfer for 6D Pose Estimationcited by 10
  32. 2023Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objectscited by 9
  33. 2020GRASPA 1.0: GRASPA is a Robot Arm graSping Performance benchmArkcited by 5
  34. 2021Designing Rotationally Invariant Neural Networks from PDEs and Variational Methodscited by 3
  35. 2024Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimationcited by 2

Built on by

Not cited yet.