mlsanityData to 14 Oct 2026

PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation

arXiv 2108.09916 ↗First posted 23 Aug 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

RGB-D based 6D pose estimation has recently achieved remarkable progress, but still suffers from two major limitations: (1) ineffective representation of depth data and (2) insufficient integration of different modalities. This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way. It first introduces the Point Refinement Network (PRN) to polish 3D point clouds, recovering missing parts with noise removed. Subsequently, the Multi-Modal Fusion Graph Convolutional Network (MMF-GCN) is presented to strengthen RGB-D combination, which captures geometry-aware inter-modality correlation through local information propagation in the graph convolutional network. Extensive experiments are conducted on three widely used benchmarks, and state-of-the-art performance is reached. Besides, it is also shown that the proposed PRN and MMF-GCN modules are well generalized to other frameworks.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 34 of its 48 references that are in the map. First posted on arXiv 23 Aug 2021.

Builds on

34 of 48 references.

References · 34

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  2. 2016Pyramid Scene Parsing Networkcited by 2,479
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  8. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2018PCN: Point Completion Networkcited by 384
  11. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  12. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
22 more
  1. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  2. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  3. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  4. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  5. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  6. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  7. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  8. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  9. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  10. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  11. 2019Single-Stage 6D Object Pose Estimationcited by 88
  12. 2019KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objectscited by 75
  13. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  14. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  15. 2014Viewpoints and Keypointscited by 59
  16. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  17. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  18. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  19. 2020G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Featurescited by 35
  20. 2016Global Hypothesis Generation for 6D Object Pose Estimationcited by 17
  21. 20206DoF Object Pose Estimation via Differentiable Proxy Voting Losscited by 7
  22. 20196D Pose Estimation with Correlation Fusioncited by 6

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 10; 2024: 1; 2025: 2.

17 papers.

Sort:

By area:

  1. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  2. 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
  3. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  4. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  5. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 17
  6. 2023Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimationcited by 16
  7. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  8. 2023FDCT: Fast Depth Completion for Transparent Objectscited by 12
  9. 2022DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimationcited by 9
  10. 2023Fusing Visual Appearance and Geometry for Multi-modality 6DoF Object Trackingcited by 7
  11. 2023Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimationcited by 7
  12. 2023TransPose: 6D Object Pose Estimation with Geometry-Aware Transformercited by 7
5 more
  1. 2023Hierarchical Graph Neural Networks for Proprioceptive 6D Pose Estimation of In-hand Objectscited by 6
  2. 2022BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimationcited by 3
  3. 2025Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimationcited by 1
  4. 2023Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Predictioncited by 0
  5. 2025DLTPose: 6DoF Pose Estimation From Accurate Dense Surface Point Estimatescited by 0