mlsanityData to 7 Oct 2026

Single-Stage Keypoint-Based Category-Level Object Pose Estimation from an RGB Image

arXiv 2109.06161 ↗First posted 13 Sep 2021cs.CV cs.ROcited by 42

Not on the map. Why?

Abstract (arXiv)

Prior work on 6-DoF object pose estimation has largely focused on instance-level processing, in which a textured CAD model is available for each object being detected. Category-level 6-DoF pose estimation represents an important step toward developing robotic vision systems that operate in unstructured, real-world scenarios. In this work, we propose a single-stage, keypoint-based approach for category-level object pose estimation that operates on unknown object instances within a known category using a single RGB image as input. The proposed network performs 2D object detection, detects 2D keypoints, estimates 6-DoF pose, and regresses relative bounding cuboid dimensions. These quantities are estimated in a sequential fashion, leveraging the recent idea of convGRU for propagating information from easier tasks to those that are more difficult. We favor simplicity in our design choices: generic cuboid vertex coordinates, single-stage network, and monocular RGB input. We conduct extensive experiments on the challenging Objectron benchmark, outperforming state-of-the-art methods on the 3D IoU metric (27.6% higher than the MobilePose single-stage approach and 7.1% higher than the related two-stage approach).

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 13 Sep 2021.

Builds on

33 of 44 references.

References · 33

  1. 2017Mask R-CNNcited by 7,259
  2. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  3. 2019Objects as Pointscited by 1,172
  4. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  5. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  7. 2017Deep Layer Aggregationcited by 436
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  10. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  11. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
21 more
  1. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  2. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  3. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  4. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  5. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  6. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  7. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 152
  8. 2015Delving Deeper into Convolutional Networks for Learning Video Representationscited by 146
  9. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  10. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  11. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  12. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  13. 20176-DoF Object Pose from Semantic Keypointscited by 89
  14. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  15. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  16. 2020CenterMask: single shot instance segmentation with point representationcited by 31
  17. 2020GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervisioncited by 28
  18. 2018Training Deep Face Recognition Systems with Synthetic Datacited by 22
  19. 2020Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learningcited by 22
  20. 2020MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervisioncited by 16
  21. 2020Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 8; 2023: 15; 2024: 6; 2025: 7; 2026: 5.

42 papers.

Sort:

By area:

  1. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  2. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 113
  3. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 113
  4. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  5. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  6. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  7. 2023HANDAL: A Dataset of Real-World Manipulable Object Categories with Pose Annotations, Affordances, and Reconstructionscited by 47
  8. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  9. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  10. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  11. 2023TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimationcited by 32
  12. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
30 more
  1. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  2. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  3. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  4. 2022Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimationcited by 19
  5. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
  6. 2023iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matchingcited by 12
  7. 2023Diff-DOPE: Differentiable Deep Object Pose Estimationcited by 11
  8. 2022Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D inputcited by 10
  9. 2023Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensorscited by 10
  10. 2023You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Examplecited by 8
  11. 2022One-Shot Neural Fields for 3D Object Understandingcited by 5
  12. 2023KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D inputcited by 4
  13. 2023Neural Textured Deformable Meshes for Robust Analysis-by-Synthesiscited by 4
  14. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 4
  15. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  16. 2024Comparative Evaluation of 3D Reconstruction Methods for Object Pose Estimationcited by 3
  17. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 3
  18. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  19. 2024A Low-Cost, High-Speed, and Robust Bin Picking System for Factory Automation Enabled by a Non-Stop, Multi-View, and Active Vision Schemecited by 2
  20. 2025SplatPose: Geometry-Aware 6-DoF Pose Estimation from Single RGB Image via 3D Gaussian Splattingcited by 2
  21. 2021SoK: Vehicle Orientation Representations for Deep Rotation Estimationcited by 1
  22. 2025You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimationcited by 1
  23. 2026Event-based Motion & Appearance Fusion for 6D Object Pose Trackingcited by 1
  24. 2023Canonical mapping as a general-purpose object descriptor for robotic manipulationcited by 0
  25. 2023AnyOKP: One-Shot and Instance-Aware Object Keypoint Extraction with Pretrained ViTcited by 0
  26. 2025Universal Features Guided Zero-Shot Category-Level Object Pose Estimationcited by 0
  27. 2026MixRI: Mixing Features of Reference Images for Novel Object Pose Estimationcited by 0
  28. 2026Demo-Pose: Depth-Monocular Modality Fusion For Object Pose Estimationcited by 0
  29. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0
  30. 2026Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objectscited by 0