mlsanityData to 14 Oct 2026

CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Network

arXiv 2303.16874 ↗First posted 29 Mar 2023cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Estimating the 6-DoF pose of a rigid object from a single RGB image is a crucial yet challenging task. Recent studies have shown the great potential of dense correspondence-based solutions, yet improvements are still needed to reach practical deployment. In this paper, we propose a novel pose estimation algorithm named CheckerPose, which improves on three main aspects. Firstly, CheckerPose densely samples 3D keypoints from the surface of the 3D object and finds their 2D correspondences progressively in the 2D image. Compared to previous solutions that conduct dense sampling in the image space, our strategy enables the correspondence searching in a 2D grid (i.e., pixel coordinate). Secondly, for our 3D-to-2D correspondence, we design a compact binary code representation for 2D image locations. This representation not only allows for progressive correspondence refinement but also converts the correspondence regression to a more efficient classification problem. Thirdly, we adopt a graph neural network to explicitly model the interactions among the sampled 3D keypoints, further boosting the reliability and accuracy of the correspondences. Together, these novel components make CheckerPose a strong pose estimation algorithm. When evaluated on the popular Linemod, Linemod-O, and YCB-V object pose estimation benchmarks, CheckerPose clearly boosts the accuracy of correspondence-based methods and achieves state-of-the-art performances. Code is available at https://github.com/RuyiLian/CheckerPose.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 55 of its 86 references that are in the map. First posted on arXiv 29 Mar 2023.

Builds on

55 of 86 references.

References · 55

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  8. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  9. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  10. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
38 more
  1. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 310
  2. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  3. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  4. 2021Mesh Graphormercited by 265
  5. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  6. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  7. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  8. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  9. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  10. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  11. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  12. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  13. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  14. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  15. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  16. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  17. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  18. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  19. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  20. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  21. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  22. 20176-DoF Object Pose from Semantic Keypointscited by 89
  23. 2019Single-Stage 6D Object Pose Estimationcited by 88
  24. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  25. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  26. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  27. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  28. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  29. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  30. 2014Viewpoints and Keypointscited by 59
  31. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  32. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  33. 2019Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithmcited by 43
  34. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  35. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  36. 2022Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transportcited by 24
  37. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  38. 2021PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimationcited by 17

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

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

15 papers.

Sort:

By area:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  2. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  3. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  4. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 17
  5. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  6. 2024VAPO: Visibility-Aware Keypoint Localization for Efficient 6DoF Object Pose Estimationcited by 1
  7. 2025Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimationcited by 1
  8. 2025RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objectscited by 1
  9. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  10. 2023Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Predictioncited by 0
  11. 2024Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Referencecited by 0
  12. 2024A Novel Convolution and Attention Mechanism-based Model for 6D Object Pose Estimationcited by 0
3 more
  1. 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generationcited by 0
  2. 2025Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perceptioncited by 0
  3. 2025DKPMV: Dense Keypoints Fusion from Multi-View RGB Frames for 6D Pose Estimation of Textureless Objectscited by 0