mlsanityData to 7 Oct 2026

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

arXiv 2303.16730 ↗First posted 29 Mar 2023cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Test-time adaptation methods have been gaining attention recently as a practical solution for addressing source-to-target domain gaps by gradually updating the model without requiring labels on the target data. In this paper, we propose a method of test-time adaptation for category-level object pose estimation called TTA-COPE. We design a pose ensemble approach with a self-training loss using pose-aware confidence. Unlike previous unsupervised domain adaptation methods for category-level object pose estimation, our approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime. Extensive experimental results demonstrate that the proposed pose ensemble and the self-training loss improve category-level object pose performance during test time under both semi-supervised and unsupervised settings. Project page: https://taeyeop.com/ttacope

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 47 of its 55 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

47 of 55 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2016Pyramid Scene Parsing Networkcited by 2,472
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  7. 2022Continual Test-Time Domain Adaptationcited by 520
  8. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  10. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  11. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
35 more
  1. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  2. 2018Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomizationcited by 292
  3. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  4. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 237
  5. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  6. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  7. 2019DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracingcited by 179
  8. 2021Source-Free Domain Adaptation for Semantic Segmentationcited by 168
  9. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  10. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  11. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  12. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  13. 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
  14. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  15. 2018MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objectscited by 95
  16. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 87
  17. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  18. 20226-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmarkcited by 85
  19. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  20. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 79
  21. 2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
  22. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  23. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 70
  24. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  25. 2022Theseus: A Library for Differentiable Nonlinear Optimizationcited by 64
  26. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  27. 2022PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objectscited by 45
  28. 2021Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Imagecited by 42
  29. 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
  30. 2021kPAM 2.0: Feedback Control for Category-Level Robotic Manipulationcited by 38
  31. 2020Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Handscited by 26
  32. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  33. 2018Kitting in the Wild through Online Domain Adaptationcited by 23
  34. 2022Test-time Adaptation with Slot-Centric Modelscited by 9
  35. 2021Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 10; 2025: 10; 2026: 5.

32 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  3. 2023HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructionscited by 47
  4. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  5. 2023In Search of Lost Online Test-time Adaptation: A Surveycited by 43
  6. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  7. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  8. 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptationcited by 25
  9. 2024HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interactioncited by 25
  10. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  11. 2023Test-Time Degradation Adaptation for Open-Set Image Restorationcited by 17
  12. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
20 more
  1. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  2. 2025Monitoring Risks in Test-Time Adaptationcited by 10
  3. 2024CRISP: Object Pose and Shape Estimation with Test-Time Adaptationcited by 9
  4. 2025UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial Referencescited by 9
  5. 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimationcited by 7
  6. 2023SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objectscited by 6
  7. 2023Deep Learning Approaches for Seizure Video Analysis: A Reviewcited by 6
  8. 2024Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Imagescited by 5
  9. 2025V-HOP: Visuo-Haptic 6D Object Pose Trackingcited by 4
  10. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 4
  11. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  12. 2025ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimationcited by 3
  13. 2025DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulationcited by 2
  14. 2026Event6D: Event-based Novel Object 6D Pose Trackingcited by 2
  15. 2025Monocular Visual 8D Pose Estimation for Articulated Bicycles and Cyclistscited by 1
  16. 2024SuperPose: Improved 6D Pose Estimation with Robust Tracking and Mask-Free Initializationcited by 0
  17. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0
  18. 2026Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimationcited by 0
  19. 2026Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptationcited by 0
  20. 2026GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Pickingcited by 0