mlsanityData to 7 Oct 2026

A Geometry-Driven, Framework-Agnostic Optimization for Object Pose Estimation

arXiv 2608.26859 ↗First posted 27 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Current object pose estimation research remains predominantly model-centric, focusing on architectural innovations and post-processing refinements. This paper introduces a data-centric optimization by proposing a novel, physically grounded rotation representation through principal axes alignment. Our method aligns the object's coordinate system with its inherent geometric axes, derived from inertial properties, yielding three key advantages: Inherent Stability-leveraging the energy-minimizing property of principal axes provides a robust representation that is less sensitive to noise and occlusions; Symmetry-Aware Canonicalization-explicitly resolving rotational ambiguities for symmetric objects at the data level, which fundamentally eliminates label confusion during network training; and Framework Agnosticism-the optimization is applied purely at the dataset level, ensuring plug-and-play compatibility with existing networks without any architectural modification. We validate the framework across diverse category-level and instance-level models. Extensive experiments demonstrate consistent and significant accuracy improvements, while preserving the integrity of the baseline network. This work establishes a new, geometry-driven direction for enhancing pose estimation, circumventing the need for complex network redesign.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 27 Aug 2026.

Builds on

35 of 46 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2024Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Dualitycited by 1,283
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  7. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  8. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  9. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  10. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
23 more
  1. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  2. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  3. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  4. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  5. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  6. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  7. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  8. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
  9. 2023UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognitioncited by 64
  10. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  11. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  12. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  13. 2020G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Featurescited by 35
  14. 2019On Object Symmetries and 6D Pose Estimation from Imagescited by 33
  15. 2021Projective Manifold Gradient Layer for Deep Rotation Regressioncited by 31
  16. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  17. 2022ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Frameworkcited by 19
  18. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  19. 2025Spectral Informed Mamba for Robust Point Cloud Processingcited by 10
  20. 2025UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial Referencescited by 9
  21. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  22. 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6
  23. 2024GatedUniPose: A Novel Approach for Pose Estimation Combining UniRepLKNet and Gated Convolutioncited by 1

Built on by

Not cited yet.