mlsanityData to 7 Oct 2026

SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation

arXiv 2106.14193 ↗First posted 27 Jun 2021cs.CV cs.ROcited by 53

Not on the map. Why?

Abstract (arXiv)

Given a single scene image, this paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data. Specifically, beyond the visual cues in RGB images, we rely on the shape information predominately from the depth (D) channel. The key idea is to explore the shape alignment of each instance against its corresponding category-level template shape, and the symmetric correspondence of each object category for estimating a coarse 3D object shape. Our framework deforms the point cloud of the category-level template shape to align the observed instance point cloud for implicitly representing its 3D rotation. Then we model the symmetric correspondence by predicting symmetric point cloud from the partially observed point cloud. The concatenation of the observed point cloud and symmetric one reconstructs a coarse object shape, thus facilitating object center (3D translation) and 3D size estimation. Extensive experiments on the category-level NOCS benchmark demonstrate that our lightweight model still competes with state-of-the-art approaches that require labeled real-world images. We also deploy our approach to a physical Baxter robot to perform grasping tasks on unseen but category-known instances, and the results further validate the efficacy of our proposed model. Code and pre-trained models are available on the project webpage.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Builds on 43 of its 65 references that are in the map. First posted on arXiv 27 Jun 2021.

Builds on

43 of 65 references.

References · 43

  1. 2017Mask R-CNNcited by 7,259
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  7. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  8. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  11. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
31 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. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  3. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  4. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  5. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  6. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  7. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  8. 2019kPAM: KeyPoint Affordances for Category-Level Robotic Manipulationcited by 152
  9. 2020PF-Net: Point Fractal Network for 3D Point Cloud Completioncited by 146
  10. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  11. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  12. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  13. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  14. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  15. 2019Self-supervised 6D Object Pose Estimation for Robot Manipulationcited by 100
  16. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  17. 20176-DoF Object Pose from Semantic Keypointscited by 89
  18. 2019Single-Stage 6D Object Pose Estimationcited by 88
  19. 2020An Analysis of SVD for Deep Rotation Estimationcited by 85
  20. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
  21. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  22. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  23. 2019Canonical Surface Mapping via Geometric Cycle Consistencycited by 62
  24. 2020MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusioncited by 46
  25. 20206D Object Pose Regression via Supervised Learning on Point Cloudscited by 33
  26. 2018Category-level 6D Object Pose Recovery in Depth Imagescited by 21
  27. 2020A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimatorscited by 18
  28. 2021StablePose: Learning 6D Object Poses from Geometrically Stable Patchescited by 17
  29. 2021CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Cloudscited by 15
  30. 2019Instance- and Category-level 6D Object Pose Estimationcited by 7
  31. 2017SUM: Sequential Scene Understanding and Manipulationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 13; 2024: 12; 2025: 14; 2026: 8.

53 papers.

Sort:

By area:

  1. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  2. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  3. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  4. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 47
  5. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  6. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 40
  7. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  8. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  9. 2022Generative Category-Level Shape and Pose Estimation with Semantic Primitivescited by 19
  10. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  11. 2024CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledgecited by 16
  12. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
38 more
  1. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 16
  2. 2024DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planningcited by 14
  3. 2023RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recoverycited by 13
  4. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 12
  5. 2023PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environmentscited by 11
  6. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 9
  7. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  8. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8
  9. 2026PoseVLA: Universal Pose Pretraining for Generalizable Vision-Language-Action Policiescited by 7
  10. 2022CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregationcited by 6
  11. 2023WALL-E: Embodied Robotic WAiter Load Lifting with Large Language Modelcited by 6
  12. 2024Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Modelscited by 6
  13. 2023DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Fieldcited by 5
  14. 2023DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimationcited by 5
  15. 2025CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Imagecited by 5
  16. 2023CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Framecited by 4
  17. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 4
  18. 2025MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learningcited by 4
  19. 2024Towards Real-World Aerial Vision Guidance with Categorical 6D Pose Trackercited by 3
  20. 2024SparseGrasp: Robotic Grasping via 3D Semantic Gaussian Splatting from Sparse Multi-View RGB Imagescited by 3
  21. 2025You Only Estimate Once: Unified, One-stage, Real-Time Category-level Articulated Object 6D Pose Estimation for Robotic Graspingcited by 3
  22. 2026ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimationcited by 3
  23. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2
  24. 2024LAC-Net: Linear-Fusion Attention-Guided Convolutional Network for Accurate Robotic Grasping Under the Occlusioncited by 2
  25. 2025Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single Viewcited by 2
  26. 2023MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimationcited by 1
  27. 2024Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimationcited by 1
  28. 2024ShapeICP: Iterative Category-level Object Pose and Shape Estimation from Depthcited by 1
  29. 2025Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimationcited by 1
  30. 2026MemPose: Category-level Object Pose Estimation with Memorycited by 1
  31. 2022Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotationscited by 0
  32. 2024Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusioncited by 0
  33. 2025Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimationcited by 0
  34. 2025AnyBox: Efficient Zero-Shot 9DoF Pose Estimation of Boxes for Robotic Manipulationcited by 0
  35. 2025THE-Pose: Topological Prior with Hybrid Graph Fusion for Estimating Category-Level 6D Object Posecited by 0
  36. 2025PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoningcited by 0
  37. 2026RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimationcited by 0
  38. 2026Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolutioncited by 0

50 most cited of 53 All 53 (JSON)