mlsanityData to 14 Oct 2026

Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation

arXiv 2503.13926 ↗First posted 18 Mar 2025cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Category-level object pose estimation aims to determine the pose and size of novel objects in specific categories. Existing correspondence-based approaches typically adopt point-based representations to establish the correspondences between primitive observed points and normalized object coordinates. However, due to the inherent shape-dependence of canonical coordinates, these methods suffer from semantic incoherence across diverse object shapes. To resolve this issue, we innovatively leverage the sphere as a shared proxy shape of objects to learn shape-independent transformation via spherical representations. Based on this insight, we introduce a novel architecture called SpherePose, which yields precise correspondence prediction through three core designs. Firstly, We endow the point-wise feature extraction with SO(3)-invariance, which facilitates robust mapping between camera coordinate space and object coordinate space regardless of rotation transformation. Secondly, the spherical attention mechanism is designed to propagate and integrate features among spherical anchors from a comprehensive perspective, thus mitigating the interference of noise and incomplete point cloud. Lastly, a hyperbolic correspondence loss function is designed to distinguish subtle distinctions, which can promote the precision of correspondence prediction. Experimental results on CAMERA25, REAL275 and HouseCat6D benchmarks demonstrate the superior performance of our method, verifying the effectiveness of spherical representations and architectural innovations.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 30 of its 45 references that are in the map. First posted on arXiv 18 Mar 2025.

Builds on

30 of 45 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2017Mask R-CNNcited by 7,277
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  8. 2020Linformer: Self-Attention with Linear Complexitycited by 1,474
  9. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  10. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  11. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  12. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
18 more
  1. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  2. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  3. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  4. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  5. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  6. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  7. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  8. 2022HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarioscited by 53
  9. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  10. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 49
  11. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 48
  12. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  13. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 41
  14. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 41
  15. 2023Improving Semantic Correspondence with Viewpoint-Guided Spherical Mapscited by 34
  16. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 13
  17. 2023MFOS: Model-Free & One-Shot Object Pose Estimationcited by 10
  18. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 6.

8 papers.

  1. 2026ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimationcited by 4
  2. 2025Structure-Aware Correspondence Learning for Relative Pose Estimationcited by 3
  3. 2025Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimationcited by 1
  4. 2026MemPose: Category-level Object Pose Estimation with Memorycited by 1
  5. 2026Object Pose Transformer: Unifying Unseen Object Pose Estimationcited by 0
  6. 2026TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimationcited by 0
  7. 2026Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolutioncited by 0
  8. 2026PriorPose: Reference-Guided Joint Deformation and Alignment for Category-Level Object Pose Estimationcited by 0