mlsanityData to 14 Oct 2026

Shape-Constraint Recurrent Flow for 6D Object Pose Estimation

arXiv 2306.13266 ↗First posted 23 Jun 2023cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object pose estimation. In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation. We first compute a pose-induced flow based on the displacement of 2D reprojection between the initial pose and the currently estimated pose, which embeds the target's 3D shape implicitly. Then we use this pose-induced flow to construct the correlation map for the following matching iterations, which reduces the matching space significantly and is much easier to learn. Furthermore, we use networks to learn the object pose based on the current estimated flow, which facilitates the computation of the pose-induced flow for the next iteration and yields an end-to-end system for object pose. Finally, we optimize the optical flow and object pose simultaneously in a recurrent manner. We evaluate our method on three challenging 6D object pose datasets and show that it outperforms the state of the art significantly in both accuracy and efficiency.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 40 of its 54 references that are in the map. First posted on arXiv 23 Jun 2023.

Builds on

40 of 54 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,546
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  5. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  6. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  7. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  8. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  9. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  11. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  12. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
28 more
  1. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  2. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  3. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  4. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  5. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  6. 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 224
  7. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  8. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  9. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  10. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  11. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  12. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  13. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  14. 2019Single-Stage 6D Object Pose Estimationcited by 88
  15. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  16. 2022CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flowcited by 82
  17. 2015EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flowcited by 80
  18. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  19. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  20. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  21. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  22. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  23. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  24. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  25. 2016Full Flow: Optical Flow Estimation By Global Optimization over Regular Gridscited by 34
  26. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  27. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  28. 2021Robust Differentiable SVDcited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 7; 2025: 5; 2026: 1.

17 papers.

Sort:

By area:

  1. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  2. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  4. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 33
  5. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  6. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  7. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  8. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 10
  9. 20256D Object Pose Tracking in Internet Videos for Robotic Manipulationcited by 10
  10. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  11. 2024Out-of-Distribution Recovery with Object-Centric Keypoint Inverse Policy for Visuomotor Imitation Learningcited by 7
  12. 2025Hierarchical Flow Diffusion for Efficient Frame Interpolationcited by 7
5 more
  1. 2024Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimationcited by 1
  2. 2024FAFA: Frequency-Aware Flow-Aided Self-Supervision for Underwater Object Pose Estimationcited by 1
  3. 2025RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objectscited by 1
  4. 2025GMatch: A Lightweight, Geometry-Constrained Keypoint Matcher for Zero-Shot 6DoF Pose Estimation in Robotic Grasp Taskscited by 0
  5. 2026Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimationcited by 0