mlsanityData to 14 Oct 2026

SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variations

arXiv 2303.10346 ↗First posted 18 Mar 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Most learning-based approaches to category-level 6D pose estimation are design around normalized object coordinate space (NOCS). While being successful, NOCS-based methods become inaccurate and less robust when handling objects of a category containing significant intra-category shape variations. This is because the object coordinates induced by global and rigid alignment of objects are semantically incoherent, making the coordinate regression hard to learn and generalize. We propose Semantically-aware Object Coordinate Space (SOCS) built by warping-and-aligning the objects guided by a sparse set of keypoints with semantically meaningful correspondence. SOCS is semantically coherent: Any point on the surface of a object can be mapped to a semantically meaningful location in SOCS, allowing for accurate pose and size estimation under large shape variations. To learn effective coordinate regression to SOCS, we propose a novel multi-scale coordinate-based attention network. Evaluations demonstrate that our method is easy to train, well-generalizing for large intra-category shape variations and robust to inter-object occlusions.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 30 of its 39 references that are in the map. First posted on arXiv 18 Mar 2023.

Builds on

30 of 39 references.

References · 30

  1. 2017Mask R-CNNcited by 7,277
  2. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  3. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  4. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  5. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  6. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  7. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  8. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  9. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  10. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  11. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  12. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
18 more
  1. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  2. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  3. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 72
  4. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 58
  5. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  6. 2021CaTGrasp: Learning Category-Level Task-Relevant Grasping in Clutter from Simulationcited by 49
  7. 2021Leveraging SE(3) Equivariance for Self-Supervised Category-Level Object Pose Estimationcited by 45
  8. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  9. 2020Unsupervised Learning of Intrinsic Structural Representation Pointscited by 39
  10. 2022Shape, Pose, and Appearance from a Single Image via Bootstrapped Radiance Field Inversioncited by 30
  11. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  12. 2021Skeleton Merger: an Unsupervised Aligned Keypoint Detectorcited by 27
  13. 2021iCaps: Iterative Category-level Object Pose and Shape Estimationcited by 23
  14. 2022Neural Correspondence Field for Object Pose Estimationcited by 21
  15. 2022Generative Category-Level Shape and Pose Estimation with Semantic Primitivescited by 19
  16. 2021DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimationcited by 12
  17. 2022Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fieldscited by 9
  18. 2022SDFEst: Categorical Pose and Shape Estimation of Objects from RGB-D using Signed Distance Fieldscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 6; 2026: 4.

13 papers.

Sort:

By area:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  2. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8
  3. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 6
  4. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 4
  5. 2025Weakly-Supervised Learning of Dense Functional Correspondencescited by 2
  6. 2023MV-ROPE: Multi-view Constraints for Robust Category-level Object Pose and Size Estimationcited by 1
  7. 2025Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Datacited by 1
  8. 2026Mind the Shape Gap: A Benchmark and Baseline for Deformation-Aware 6D Pose Estimation of Agricultural Producecited by 1
  9. 2024Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Referencecited by 0
  10. 2025Category-Level and Open-Set Object Pose Estimation for Roboticscited by 0
  11. 2026Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimationcited by 0
  12. 2026MoCA3D: Monocular 3D Bounding Box Prediction in the Image Planecited by 0
1 more
  1. 2026SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schemacited by 0