mlsanityData to 7 Oct 2026

Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networks

arXiv 2108.08755 ↗First posted 19 Aug 2021cs.CVcited by 69

Not on the map. Why?

Abstract (arXiv)

Category-level 6D pose estimation, aiming to predict the location and orientation of unseen object instances, is fundamental to many scenarios such as robotic manipulation and augmented reality, yet still remains unsolved. Precisely recovering instance 3D model in the canonical space and accurately matching it with the observation is an essential point when estimating 6D pose for unseen objects. In this paper, we achieve accurate category-level 6D pose estimation via cascaded relation and recurrent reconstruction networks. Specifically, a novel cascaded relation network is dedicated for advanced representation learning to explore the complex and informative relations among instance RGB image, instance point cloud and category shape prior. Furthermore, we design a recurrent reconstruction network for iterative residual refinement to progressively improve the reconstruction and correspondence estimations from coarse to fine. Finally, the instance 6D pose is obtained leveraging the estimated dense correspondences between the instance point cloud and the reconstructed 3D model in the canonical space. We have conducted extensive experiments on two well-acknowledged benchmarks of category-level 6D pose estimation, with significant performance improvement over existing approaches. On the representatively strict evaluation metrics of 3D75 and 5circ2 cm, our method exceeds the latest state-of-the-art SPD by 4.9% and 17.7% on the CAMERA25 dataset, and by 2.7% and 8.5% on the REAL275 dataset. Codes are available at https://wangjiaze.cn/projects/6DPoseEstimation.html.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

33 of 47 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2017Mask R-CNNcited by 7,259
  5. 2016Pyramid Scene Parsing Networkcited by 2,472
  6. 2017Non-local Neural Networkscited by 2,290
  7. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  8. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  9. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  10. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  11. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  12. 2017A simple neural network module for relational reasoningcited by 345
21 more
  1. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  2. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  3. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  4. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  5. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  6. 2020MovieNet: A Holistic Dataset for Movie Understandingcited by 206
  7. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  8. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  9. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  10. 2015Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Imagescited by 111
  11. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  12. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  13. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  14. 2020A Local-to-Global Approach to Multi-modal Movie Scene Segmentationcited by 60
  15. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  16. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  17. 2020A Unified Framework for Shot Type Classification Based on Subject Centric Lenscited by 44
  18. 2018Category-level 6D Object Pose Recovery in Depth Imagescited by 21
  19. 2020Online Multi-modal Person Search in Videoscited by 10
  20. 2020Robust RGB-based 6-DoF Pose Estimation without Real Pose Annotationscited by 5
  21. 2019Probabilistic Category-Level Pose Estimation via Segmentation and Predicted-Shape Priorscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 14; 2023: 19; 2024: 14; 2025: 12; 2026: 6.

69 papers.

Sort:

By area:

  1. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  2. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 135
  3. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  4. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  5. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  6. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  7. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 48
  8. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  9. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 47
  10. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  11. 2023Traj-MAE: Masked Autoencoders for Trajectory Predictioncited by 42
  12. 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
38 more
  1. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  2. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 40
  3. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 40
  4. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  5. 2023TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimationcited by 32
  6. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 28
  7. 2021UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimationcited by 25
  8. 20216D-ViT: Category-Level 6D Object Pose Estimation via Transformer-based Instance Representation Learningcited by 20
  9. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  10. 2022Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Pickingcited by 20
  11. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  12. 2023Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimationcited by 16
  13. 2024CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledgecited by 16
  14. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  15. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 16
  16. 2023Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selectioncited by 14
  17. 2023RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recoverycited by 13
  18. 2021A Review for Deep Reinforcement Learning in Atari:Benchmarks, Challenges, and Solutionscited by 12
  19. 2023GS-Pose: Category-Level Object Pose Estimation via Geometric and Semantic Correspondencecited by 12
  20. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  21. 2022Towards Self-Supervised Category-Level Object Pose and Size Estimationcited by 11
  22. 2023MFOS: Model-Free & One-Shot Object Pose Estimationcited by 10
  23. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimationcited by 10
  24. 2022A Visual Navigation Perspective for Category-Level Object Pose Estimationcited by 8
  25. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  26. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8
  27. 2022SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fieldscited by 7
  28. 2024Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimationcited by 7
  29. 2022Optimal and Robust Category-level Perception: Object Pose and Shape Estimation from 2D and 3D Semantic Keypointscited by 6
  30. 2024Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Modelscited by 6
  31. 2023DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Fieldcited by 5
  32. 2023DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimationcited by 5
  33. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 5
  34. 2023PointPatchMix: Point Cloud Mixing with Patch Scoringcited by 4
  35. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 4
  36. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  37. 2022On the Evaluation of RGB-D-based Categorical Pose and Shape Estimationcited by 2
  38. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2

50 most cited of 69 All 69 (JSON)