# Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation

arXiv: https://arxiv.org/abs/2203.09836 · HTML: https://mlsanity.com/paper/2203.09836/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 58 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 30 of 39)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [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)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [CosyPose: Consistent multi-view multi-object 6D pose estimation](https://mlsanity.com/paper/2008.08465/) (2020)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [BOP: Benchmark for 6D Object Pose Estimation](https://mlsanity.com/paper/1808.08319/) (2018)
- [SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again](https://mlsanity.com/paper/1711.10006/) (2017)
- [BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depth](https://mlsanity.com/paper/1703.10896/) (2017)
- [Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation](https://mlsanity.com/paper/1908.07433/) (2019)
- [Real-Time Seamless Single Shot 6D Object Pose Prediction](https://mlsanity.com/paper/1711.08848/) (2017)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [DPOD: 6D Pose Object Detector and Refiner](https://mlsanity.com/paper/1902.11020/) (2019)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [EPOS: Estimating 6D Pose of Objects with Symmetries](https://mlsanity.com/paper/2004.00605/) (2020)
- [GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator](https://mlsanity.com/paper/2102.12145/) (2021)
- [Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering](https://mlsanity.com/paper/2003.08607/) (2020)
- [Gradually Vanishing Bridge for Adversarial Domain Adaptation](https://mlsanity.com/paper/2003.13183/) (2020)
- [HybridPose: 6D Object Pose Estimation under Hybrid Representations](https://mlsanity.com/paper/2001.01869/) (2020)
- [Segmentation-driven 6D Object Pose Estimation](https://mlsanity.com/paper/1812.02541/) (2018)
- [Single-Stage 6D Object Pose Estimation](https://mlsanity.com/paper/1911.08324/) (2019)
- [SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation](https://mlsanity.com/paper/2108.08367/) (2021)
- [EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow](https://mlsanity.com/paper/1501.02565/) (2015)
- [Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimation](https://mlsanity.com/paper/1804.03959/) (2018)

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

- [BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects](https://mlsanity.com/paper/2302.13075/) (2023)
- [BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects](https://mlsanity.com/paper/2403.09799/) (2024)
- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects](https://mlsanity.com/paper/2403.11510/) (2024)
- [Challenges for Monocular 6D Object Pose Estimation in Robotics](https://mlsanity.com/paper/2307.12172/) (2023)
- [Shape-Constraint Recurrent Flow for 6D Object Pose Estimation](https://mlsanity.com/paper/2306.13266/) (2023)
- [HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation](https://mlsanity.com/paper/2311.12588/) (2023)
- [CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network](https://mlsanity.com/paper/2303.16874/) (2023)
- [LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation](https://mlsanity.com/paper/2409.15727/) (2024)
- [Co-op: Correspondence-based Novel Object Pose Estimation](https://mlsanity.com/paper/2503.17731/) (2025)
- [Rigidity-Aware Detection for 6D Object Pose Estimation](https://mlsanity.com/paper/2303.12396/) (2023)
- [MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation](https://mlsanity.com/paper/2403.08019/) (2024)
- [COPE: End-to-end trainable Constant Runtime Object Pose Estimation](https://mlsanity.com/paper/2208.08807/) (2022)
- [Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation](https://mlsanity.com/paper/2308.10016/) (2023)
- [UniHOPE: A Unified Approach for Hand-Only and Hand-Object Pose Estimation](https://mlsanity.com/paper/2503.13303/) (2025)
- [Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation](https://mlsanity.com/paper/2311.09500/) (2023)
- [Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera](https://mlsanity.com/paper/2405.05858/) (2024)
- [Synthetica: Large Scale Synthetic Data for Robot Perception](https://mlsanity.com/paper/2410.21153/) (2024)
- [HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimation](https://mlsanity.com/paper/2510.10177/) (2025)
- [Open Challenges for Monocular Single-shot 6D Object Pose Estimation](https://mlsanity.com/paper/2302.11827/) (2023)
- [Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimation](https://mlsanity.com/paper/2402.04878/) (2024)
- [End-to-End Probabilistic Geometry-Guided Regression for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2409.11819/) (2024)
- [PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens](https://mlsanity.com/paper/2311.17504/) (2023)
- [Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimation](https://mlsanity.com/paper/2401.16284/) (2024)
- [FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation](https://mlsanity.com/paper/2409.16600/) (2024)
- [SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow](https://mlsanity.com/paper/2504.09160/) (2025)
- [RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects](https://mlsanity.com/paper/2505.10841/) (2025)
- [Generative 6D Pose Estimation via Conditional Flow Matching](https://mlsanity.com/paper/2602.19719/) (2026)
- [FAST GDRNPP: Improving the Speed of State-of-the-Art 6D Object Pose Estimation](https://mlsanity.com/paper/2409.12720/) (2024)
- [DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimates](https://mlsanity.com/paper/2504.07335/) (2025)

## Abstract (arXiv)

Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep under water, acquiring real images, even unannotated, is virtually impossible. In this paper, we propose a method that can be trained solely on synthetic images, or optionally using a few additional real ones. Given a rough pose estimate obtained from a first network, it uses a second network to predict a dense 2D correspondence field between the image rendered using the rough pose and the real image and infers the required pose correction. This approach is much less sensitive to the domain shift between synthetic and real images than state-of-the-art methods. It performs on par with methods that require annotated real images for training when not using any, and outperforms them considerably when using as few as twenty real images.