mlsanityData to 14 Oct 2026

TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimation

arXiv 2604.16954 ↗First posted 18 Apr 2026cs.CVcited by 0

On the map: State-space sequence models (S4, Mamba) → Video, motion and generative Mamba models

Abstract (arXiv)

Category-level object pose estimation is fundamental for embodied intelligence, yet achieving robust generalization to unseen instances remains challenging. However, existing methods mainly rely on simple feature extraction and aggregation, which struggle to capture category-shared topological structures and conduct semantic keypoint modeling, limiting their generalization. To address these, we propose a Topology-Aware Learning with Semantic Mamba for Category-Level Pose Estimation framework (TSM-Pose). Specifically, we introduce a Topology Extractor to capture the global topological representation of the point cloud, which is integrated into local geometry features and enables robust category-level structural representation. Simultaneously, we propose a Mamba-based Global Semantic Aggregator that injects semantics priors into keypoints to enhance their expressiveness and leverages multiple TwinMamba blocks to model long-range dependencies for more effective global feature aggregation. Extensive experiments on three benchmark datasets (REAL275, CAMERA25, and HouseCat6D) demonstrate that TSM-Pose outperforms existing state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video, motion and generative Mamba models, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 29 of its 44 references that are in the map. First posted on arXiv 18 Apr 2026.

Builds on

29 of 44 references.

References · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,056
  6. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  8. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  9. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  10. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  11. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 81
  12. 2020Data Poisoning Attacks on Federated Machine Learningcited by 62
17 more
  1. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  2. 2022HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarioscited by 53
  3. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 53
  4. 2025Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigationcited by 51
  5. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 43
  6. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 41
  7. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 29
  8. 2020Grasp Proposal Networks: An End-to-End Solution for Visual Learning of Robotic Graspscited by 22
  9. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  10. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 18
  11. 2024Functionality understanding and segmentation in 3D scenescited by 17
  12. 2024CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledgecited by 16
  13. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  14. 2025Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimationcited by 8
  15. 2025MK-Pose: Category-Level Object Pose Estimation via Multimodal-Based Keypoint Learningcited by 4
  16. 2025Robust Model Reconstruction Based on the Topological Understanding of Point Clouds Using Persistent Homologycited by 2
  17. 2025TACO-Net: Topological Signatures Triumph in 3D Object Classificationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Mamba-Driven Topology Fusion for Monocular 3D Human Pose Estimation
  2. 2025Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimation
  3. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Models
  4. 2025A Structure-aware and Motion-adaptive Framework for 3D Human Pose Estimation with Mamba
  5. 2022A Visual Navigation Perspective for Category-Level Object Pose Estimation
  6. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimation
  7. 2024PoseMamba: Monocular 3D Human Pose Estimation with Bidirectional Global-Local Spatio-Temporal State Space Model
  8. 2024OV9D: Open-Vocabulary Category-Level 9D Object Pose and Size Estimation