mlsanityData to 14 Oct 2026

Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolution

arXiv 2606.02219 ↗First posted 1 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Object pose estimation is a fundamental problem for an agent system to perceive or manipulate objects in images or videos. However, current instance-level methods struggle with generalization to unseen objects. Category-level methods seek to address this, but remain constrained by the complexities of learning in the non-linear Sim(3) space and intra-class variations. To address these challenges, We propose an effective method for category-level object pose estimation with two key innovations: (1) A translation/size estimator, featuring a semantic-guided symmetry-aware module that leverages robust generalization capabilities of a large vision model (LVM) to infer symmetry points, resulting in accurate translation and size without shape priors. This result serves as a precomputed cue for rotation estimation, thereby reducing the difficulty of learning in the non-linear Sim(3) space and laying a robust foundation for tackling the inherently more challenging rotation estimation. (2) A feature fusion module, based on our proposed spherical large-kernel inception convolution, fuses semantic features from the LVM with systematically computed geometric features to extract essential pose features from intra-class variations by modeling long-range dependencies without excessive computational cost. Built on these innovations, we achieve SOTA on benchmarks and real-world scenes, while developing a robust robotic picking system capable of handling diverse objects. Our code will be available at the project page: hypersetupurlcolor=bluehttps://panfei-cheng.github.io/SSH-Pose.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 49 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

26 of 49 references.

References · 26

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2017Mask R-CNNcited by 7,277
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  5. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  7. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  8. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  9. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  10. 2023InceptionNeXt: When Inception Meets ConvNeXtcited by 86
  11. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  12. 2022CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimationcited by 70
14 more
  1. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  2. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  3. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  4. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 49
  5. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  6. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 41
  7. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 41
  8. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 40
  9. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  10. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited 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
  13. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  14. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8

Built on by

Not cited yet.