mlsanityData to 14 Oct 2026

RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization

arXiv 2203.12870 ↗First posted 24 Mar 2022cs.CV cs.ROcited by 38

Not on the map. Why?

Abstract (arXiv)

6-DoF object pose estimation from a monocular image is challenging, and a post-refinement procedure is generally needed for high-precision estimation. In this paper, we propose a framework based on a recurrent neural network (RNN) for object pose refinement, which is robust to erroneous initial poses and occlusions. During the recurrent iterations, object pose refinement is formulated as a non-linear least squares problem based on the estimated correspondence field (between a rendered image and the observed image). The problem is then solved by a differentiable Levenberg-Marquardt (LM) algorithm enabling end-to-end training. The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover the object poses. Furthermore, to improve the robustness to occlusion, we introduce a consistency-check mechanism based on the learned descriptors of the 3D model and observed 2D images, which downweights the unreliable correspondences during pose optimization. Extensive experiments on LINEMOD, Occlusion-LINEMOD, and YCB-Video datasets validate the effectiveness of our method and demonstrate state-of-the-art performance.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 24 Mar 2022.

Builds on

49 of 62 references.

References · 49

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2017Mask R-CNNcited by 7,277
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  10. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  11. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  12. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
37 more
  1. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  2. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  4. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 403
  5. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  6. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  7. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  8. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  9. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  10. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  11. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  12. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  13. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  14. 2017UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Losscited by 202
  15. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  16. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  17. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  18. 2018BA-Net: Dense Bundle Adjustment Networkcited by 175
  19. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  20. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  21. 2019SelFlow: Self-Supervised Learning of Optical Flowcited by 128
  22. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  23. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  24. 2019Single-Stage 6D Object Pose Estimationcited by 88
  25. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  26. 2020SSN: Shape Signature Networks for Multi-class Object Detection from Point Cloudscited by 74
  27. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  28. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  29. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  30. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  31. 2021Tangent Space Backpropagation for 3D Transformation Groupscited by 40
  32. 2019GN-Net: The Gauss-Newton Loss for Multi-Weather Relocalizationcited by 32
  33. 2021VS-Net: Voting with Segmentation for Visual Localizationcited by 29
  34. 2020SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloudcited by 16
  35. 2020Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wildcited by 10
  36. 2022Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modelingcited by 6
  37. 2021PDNet: Toward Better One-Stage Object Detection With Prediction Decouplingcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 14; 2024: 7; 2025: 5; 2026: 5.

38 papers.

Sort:

  1. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 275
  2. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  3. 2022Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoningcited by 69
  4. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 49
  5. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  6. 2023PATS: Patch Area Transportation with Subdivision for Local Feature Matchingcited by 33
  7. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  8. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  9. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  10. 2023RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recoverycited by 14
  11. 2025Do It Yourself: Learning Semantic Correspondence from Pseudo-Labelscited by 13
  12. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
26 more
  1. 2025MATCHA:Towards Matching Anythingcited by 12
  2. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  3. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  4. 2023Depth-based 6DoF Object Pose Estimation using Swin Transformercited by 8
  5. 2022Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulationcited by 6
  6. 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6
  7. 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypothesescited by 6
  8. 2024Advancing 6-DoF Instrument Pose Estimation in Variable X-Ray Imaging Geometriescited by 3
  9. 2025QORT-Former: Query-optimized Real-time Transformer for Understanding Two Hands Manipulating Objectscited by 3
  10. 2022Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labelscited by 2
  11. 2023Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Posecited by 2
  12. 2023For A More Comprehensive Evaluation of 6DoF Object Pose Trackingcited by 2
  13. 2022DeepRM: Deep Recurrent Matching for 6D Pose Refinementcited by 1
  14. 2022PixTrack: Precise 6DoF Object Pose Tracking using NeRF Templates and Feature-metric Alignmentcited by 1
  15. 2023MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimationcited by 1
  16. 2024Leveraging Positional Encoding for Robust Multi-Reference-Based Object 6D Pose Estimationcited by 1
  17. 2022A Flexible-Frame-Rate Vision-Aided Inertial Object Tracking System for Mobile Devicescited by 0
  18. 2024Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Referencecited by 0
  19. 2024A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimationcited by 0
  20. 2025DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera Scenarioscited by 0
  21. 2025Active Control Points-based 6DoF Pose Tracking for Industrial Metal Objectscited by 0
  22. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0
  23. 2026Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancementscited by 0
  24. 2026Temporally Consistent Object 6D Pose Estimation for Robot Controlcited by 0
  25. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0
  26. 2026DirtyMoCap: Robust Motion Capture from Unconstrained Markerscited by 0