mlsanityData to 7 Oct 2026

CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillation

arXiv 2502.01312 ↗First posted 3 Feb 2025cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Category-level object pose estimation aims to recover the rotation, translation and size of unseen instances within predefined categories. In this task, deep neural network-based methods have demonstrated remarkable performance. However, previous studies show they suffer from spurious correlations raised by "unclean" confounders in models, hindering their performance on novel instances with significant variations. To address this issue, we propose CleanPose, a novel approach integrating causal learning and knowledge distillation to enhance category-level pose estimation. To mitigate the negative effect of unobserved confounders, we develop a causal inference module based on front-door adjustment, which promotes unbiased estimation by reducing potential spurious correlations. Additionally, to further improve generalization ability, we devise a residual-based knowledge distillation method that has proven effective in providing comprehensive category information guidance. Extensive experiments across multiple benchmarks (REAL275, CAMERA25 and HouseCat6D) hightlight the superiority of proposed CleanPose over state-of-the-art methods. Code will be available at https://github.com/chrislin0621/CleanPose.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 49 of its 62 references that are in the map. First posted on arXiv 3 Feb 2025.

Builds on

49 of 62 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2017Mask R-CNNcited by 7,259
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  10. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  11. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  12. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
37 more
  1. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  2. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  3. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  4. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 199
  5. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  6. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  7. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  8. 2021Causal Attention for Vision-Language Taskscited by 111
  9. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  10. 2021Causal Attention for Unbiased Visual Recognitioncited by 80
  11. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  12. 2020Deconfounded Image Captioning: A Causal Retrospectcited by 65
  13. 2022Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Datasetcited by 59
  14. 2022Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answeringcited by 57
  15. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  16. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  17. 2022HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarioscited by 51
  18. 2024Vision-and-Language Navigation via Causal Learningcited by 51
  19. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  20. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 47
  21. 2022PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objectscited by 45
  22. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  23. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 40
  24. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 40
  25. 2024FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognitioncited by 35
  26. 2022CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinementcited by 28
  27. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23
  28. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  29. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  30. 2024CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledgecited by 16
  31. 2024SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detectioncited by 14
  32. 2022Structural Causal 3D Reconstructioncited by 12
  33. 2024Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimationcited by 11
  34. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  35. 2023Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learningcited by 7
  36. 2023TransPose: 6D Object Pose Estimation with Geometry-Aware Transformercited by 7
  37. 2024MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfercited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 7.

9 papers.

  1. 2025Distilling 3D distinctive local descriptors for 6D pose estimationcited by 4
  2. 2026ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimationcited by 3
  3. 2025Instance-Adaptive Keypoint Learning with Local-to-Global Geometric Aggregation for Category-Level Object Pose Estimationcited by 1
  4. 2026CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Posecited by 1
  5. 2026CIGPose: Causal Intervention Graph Neural Network for Whole-Body Pose Estimationcited by 1
  6. 2026MemPose: Category-level Object Pose Estimation with Memorycited by 1
  7. 2026DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimationcited by 0
  8. 2026UniPose9D: Universal Category-Agnostic Object Pose Estimationcited by 0
  9. 2026GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Pickingcited by 0