# Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation

arXiv: https://arxiv.org/abs/2308.10016 · HTML: https://mlsanity.com/paper/2308.10016/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 66 references that are in the map.
- First posted on arXiv 19 Aug 2023.

## Builds on (most cited first, 30 of 52)

- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes](https://mlsanity.com/paper/1711.00199/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [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)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (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)
- [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)
- [UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss](https://mlsanity.com/paper/1711.07837/) (2017)
- [GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator](https://mlsanity.com/paper/2102.12145/) (2021)
- [ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape](https://mlsanity.com/paper/1812.02781/) (2018)
- [Humble Teachers Teach Better Students for Semi-Supervised Object Detection](https://mlsanity.com/paper/2106.10456/) (2021)
- [ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation](https://mlsanity.com/paper/2203.09418/) (2022)
- [Segmentation-driven 6D Object Pose Estimation](https://mlsanity.com/paper/1812.02541/) (2018)
- [SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings](https://mlsanity.com/paper/2111.13489/) (2021)
- [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)
- [Self6D: Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2004.06468/) (2020)
- [EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation](https://mlsanity.com/paper/2303.12787/) (2023)
- [SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping](https://mlsanity.com/paper/2105.07014/) (2021)
- [BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects](https://mlsanity.com/paper/2302.13075/) (2023)
- [End-to-End Learnable Geometric Vision by Backpropagating PnP Optimization](https://mlsanity.com/paper/1909.06043/) (2019)

## Built on by (most cited first, 9 of 9)

- [Deep Learning-Based Object Pose Estimation: A Comprehensive Survey](https://mlsanity.com/paper/2405.07801/) (2024)
- [Hierarchical Flow Diffusion for Efficient Frame Interpolation](https://mlsanity.com/paper/2504.00380/) (2025)
- [Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Camera](https://mlsanity.com/paper/2503.20207/) (2025)
- [Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimation](https://mlsanity.com/paper/2403.12728/) (2024)
- [FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimation](https://mlsanity.com/paper/2409.16600/) (2024)
- [Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching](https://mlsanity.com/paper/2411.15860/) (2024)
- [SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow](https://mlsanity.com/paper/2504.09160/) (2025)
- [Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancements](https://mlsanity.com/paper/2603.03879/) (2026)
- [ComPose: When to Trust Hands for Object Pose Tracking](https://mlsanity.com/paper/2605.23523/) (2026)

## Abstract (arXiv)

Most self-supervised 6D object pose estimation methods can only work with additional depth information or rely on the accurate annotation of 2D segmentation masks, limiting their application range. In this paper, we propose a 6D object pose estimation method that can be trained with pure RGB images without any auxiliary information. We first obtain a rough pose initialization from networks trained on synthetic images rendered from the target's 3D mesh. Then, we introduce a refinement strategy leveraging the geometry constraint in synthetic-to-real image pairs from multiple different views. We formulate this geometry constraint as pixel-level flow consistency between the training images with dynamically generated pseudo labels. We evaluate our method on three challenging datasets and demonstrate that it outperforms state-of-the-art self-supervised methods significantly, with neither 2D annotations nor additional depth images.