mlsanityData to 14 Oct 2026

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

arXiv 2308.10016 ↗First posted 19 Aug 2023cs.CVcited by 9

Not on the map. Why?

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.

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

52 of 66 references.

References · 52

  1. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  2. 2017Mask R-CNNcited by 7,277
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  8. 2017Neural 3D Mesh Renderercited by 437
  9. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  10. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  11. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 316
  12. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
38 more
  1. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  2. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  3. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  4. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  5. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  6. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  7. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  8. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
  9. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  10. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  11. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  12. 2019Single-Stage 6D Object Pose Estimationcited by 88
  13. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  14. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  15. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  16. 2021SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warpingcited by 74
  17. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  18. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  19. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  20. 2022Semi-supervised Semantic Segmentation with Error Localization Networkcited by 57
  21. 2022PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detectioncited by 51
  22. 2018Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspectivecited by 50
  23. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  24. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  25. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  26. 2021StereOBJ-1M: Large-scale Stereo Image Dataset for 6D Object Pose Estimationcited by 40
  27. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  28. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  29. 2017LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenescited by 32
  30. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  31. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  32. 2022Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimationcited by 28
  33. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  34. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  35. 2022Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Pickingcited by 20
  36. 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
  37. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  38. 2021DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-scale Consistencycited by 14

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 2.

9 papers.

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  2. 2025Hierarchical Flow Diffusion for Efficient Frame Interpolationcited by 7
  3. 2025Reasoning and Learning a Perceptual Metric for Self-Training of Reflective Objects in Bin-Picking with a Low-cost Cameracited by 2
  4. 2024Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimationcited by 1
  5. 2024FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimationcited by 1
  6. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  7. 2025SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flowcited by 1
  8. 2026Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancementscited by 0
  9. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0