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

arXiv: https://arxiv.org/abs/2303.16730 · HTML: https://mlsanity.com/paper/2303.16730/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 55 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 30 of 47)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (2019)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1812.11788/) (2018)
- [DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion](https://mlsanity.com/paper/1901.04780/) (2019)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects](https://mlsanity.com/paper/1809.10790/) (2018)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare](https://mlsanity.com/paper/2212.06870/) (2022)
- [DIST: Rendering Deep Implicit Signed Distance Function with Differentiable Sphere Tracing](https://mlsanity.com/paper/1911.13225/) (2019)
- [Source-Free Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2103.16372/) (2021)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations](https://mlsanity.com/paper/2012.09988/) (2020)
- [xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/1911.12676/) (2019)
- [Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2001.09322/) (2020)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency](https://mlsanity.com/paper/2103.06526/) (2021)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains](https://mlsanity.com/paper/2007.13866/) (2020)
- [BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models](https://mlsanity.com/paper/2108.00516/) (2021)
- [6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark](https://mlsanity.com/paper/2203.05701/) (2022)

## Built on by (most cited first, 30 of 32)

- [FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects](https://mlsanity.com/paper/2312.08344/) (2023)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Any6D: Model-free 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2503.18673/) (2025)
- [HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructions](https://mlsanity.com/paper/2308.01477/) (2023)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimation](https://mlsanity.com/paper/2403.19527/) (2024)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction](https://mlsanity.com/paper/2406.06843/) (2024)
- [BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation](https://mlsanity.com/paper/2402.08712/) (2024)
- [InterTrack: Tracking Human Object Interaction without Object Templates](https://mlsanity.com/paper/2408.13953/) (2024)
- [Test-Time Degradation Adaptation for Open-Set Image Restoration](https://mlsanity.com/paper/2312.02197/) (2023)
- [Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation](https://mlsanity.com/paper/2502.02525/) (2025)
- [Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integration](https://mlsanity.com/paper/2503.05578/) (2025)
- [Monitoring Risks in Test-Time Adaptation](https://mlsanity.com/paper/2507.08721/) (2025)
- [CRISP: Object Pose and Shape Estimation with Test-Time Adaptation](https://mlsanity.com/paper/2412.01052/) (2024)
- [UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References](https://mlsanity.com/paper/2506.07996/) (2025)
- [Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation](https://mlsanity.com/paper/2401.10848/) (2024)
- [SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects](https://mlsanity.com/paper/2308.16528/) (2023)
- [Deep Learning Approaches for Seizure Video Analysis: A Review](https://mlsanity.com/paper/2312.10930/) (2023)
- [Category-level Object Detection, Pose Estimation and Reconstruction from Stereo Images](https://mlsanity.com/paper/2407.06984/) (2024)
- [V-HOP: Visuo-Haptic 6D Object Pose Tracking](https://mlsanity.com/paper/2502.17434/) (2025)
- [MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model](https://mlsanity.com/paper/2504.10433/) (2025)
- [Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Tracker](https://mlsanity.com/paper/2401.04377/) (2024)
- [ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation](https://mlsanity.com/paper/2504.13179/) (2025)
- [DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation](https://mlsanity.com/paper/2510.05662/) (2025)
- [Event6D: Event-based Novel Object 6D Pose Tracking](https://mlsanity.com/paper/2603.28045/) (2026)
- [Monocular Visual 8D Pose Estimation for Articulated Bicycles and Cyclists](https://mlsanity.com/paper/2510.20158/) (2025)
- [SuperPose: Improved 6D Pose Estimation with Robust Tracking and Mask-Free Initialization](https://mlsanity.com/paper/2409.19986/) (2024)
- [MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation](https://mlsanity.com/paper/2601.06883/) (2026)
- [Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimation](https://mlsanity.com/paper/2601.13565/) (2026)

## 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