# Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation

arXiv: https://arxiv.org/abs/2401.10848 · HTML: https://mlsanity.com/paper/2401.10848/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 46 references that are in the map.
- First posted on arXiv 19 Jan 2024.

## Builds on (most cited first, 30 of 34)

- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/1901.02970/) (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)
- [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)
- [PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation](https://mlsanity.com/paper/1911.04231/) (2019)
- [Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2007.08454/) (2020)
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://mlsanity.com/paper/2103.02242/) (2021)
- [Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation](https://mlsanity.com/paper/2001.09322/) (2020)
- [Differentiable Rendering: A Survey](https://mlsanity.com/paper/2006.12057/) (2020)
- [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)
- [Category Level Object Pose Estimation via Neural Analysis-by-Synthesis](https://mlsanity.com/paper/2008.08145/) (2020)
- [MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects](https://mlsanity.com/paper/1804.09194/) (2018)
- [6-DoF Object Pose from Semantic Keypoints](https://mlsanity.com/paper/1703.04670/) (2017)
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://mlsanity.com/paper/2207.05444/) (2022)
- [Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challenge](https://mlsanity.com/paper/1609.09475/) (2016)
- [Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks](https://mlsanity.com/paper/2108.08755/) (2021)
- [RePOSE: Fast 6D Object Pose Refinement via Deep Texture Rendering](https://mlsanity.com/paper/2104.00633/) (2021)
- [Zero-Shot Category-Level Object Pose Estimation](https://mlsanity.com/paper/2204.03635/) (2022)
- [Robust Object Detection under Occlusion with Context-Aware CompositionalNets](https://mlsanity.com/paper/2005.11643/) (2020)
- [Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion](https://mlsanity.com/paper/2003.04490/) (2020)
- [StarMap for Category-Agnostic Keypoint and Viewpoint Estimation](https://mlsanity.com/paper/1803.09331/) (2018)
- [NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation](https://mlsanity.com/paper/2101.12378/) (2021)
- [TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation](https://mlsanity.com/paper/2303.16730/) (2023)
- [SegICP: Integrated Deep Semantic Segmentation and Pose Estimation](https://mlsanity.com/paper/1703.01661/) (2017)
- [UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation](https://mlsanity.com/paper/2111.12580/) (2021)
- [Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features](https://mlsanity.com/paper/2209.05624/) (2022)
- [Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild](https://mlsanity.com/paper/2210.07199/) (2022)

## Built on by (most cited first, 7 of 7)

- [The Universal Weight Subspace Hypothesis](https://mlsanity.com/paper/2512.05117/) (2025)
- [Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering](https://mlsanity.com/paper/2406.00622/) (2024)
- [EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference](https://mlsanity.com/paper/2502.04700/) (2025)
- [A Bayesian Approach to OOD Robustness in Image Classification](https://mlsanity.com/paper/2403.07277/) (2024)
- [Name That Part: 3D Part Segmentation and Naming](https://mlsanity.com/paper/2512.18003/) (2025)
- [Shared LoRA Subspaces for almost Strict Continual Learning](https://mlsanity.com/paper/2602.06043/) (2026)
- [Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Reference](https://mlsanity.com/paper/2406.18453/) (2024)

## Abstract (arXiv)

We consider the problem of source-free unsupervised category-level pose estimation from only RGB images to a target domain without any access to source domain data or 3D annotations during adaptation. Collecting and annotating real-world 3D data and corresponding images is laborious, expensive, yet unavoidable process, since even 3D pose domain adaptation methods require 3D data in the target domain. We introduce 3DUDA, a method capable of adapting to a nuisance-ridden target domain without 3D or depth data. Our key insight stems from the observation that specific object subparts remain stable across out-of-domain (OOD) scenarios, enabling strategic utilization of these invariant subcomponents for effective model updates. We represent object categories as simple cuboid meshes, and harness a generative model of neural feature activations modeled at each mesh vertex learnt using differential rendering. We focus on individual locally robust mesh vertex features and iteratively update them based on their proximity to corresponding features in the target domain even when the global pose is not correct. Our model is then trained in an EM fashion, alternating between updating the vertex features and the feature extractor. We show that our method simulates fine-tuning on a global pseudo-labeled dataset under mild assumptions, which converges to the target domain asymptotically. Through extensive empirical validation, including a complex extreme UDA setup which combines real nuisances, synthetic noise, and occlusion, we demonstrate the potency of our simple approach in addressing the domain shift challenge and significantly improving pose estimation accuracy.