mlsanityData to 7 Oct 2026

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

arXiv 2207.08082 ↗First posted 17 Jul 2022cs.CVcited by 28

Not on the map. Why?

Abstract (arXiv)

While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc. Orthogonal to them, this work presents a category-level object pose and size refiner CATRE, which is able to iteratively enhance pose estimate from point clouds to produce accurate results. Given an initial pose estimate, CATRE predicts a relative transformation between the initial pose and ground truth by means of aligning the partially observed point cloud and an abstract shape prior. In specific, we propose a novel disentangled architecture being aware of the inherent distinctions between rotation and translation/size estimation. Extensive experiments show that our approach remarkably outperforms state-of-the-art methods on REAL275, CAMERA25, and LM benchmarks up to a speed of ~85.32Hz, and achieves competitive results on category-level tracking. We further demonstrate that CATRE can perform pose refinement on unseen category. Code and trained models are available.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 47 of its 65 references that are in the map. First posted on arXiv 17 Jul 2022.

Builds on

47 of 65 references.

References · 47

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Mask R-CNNcited by 7,259
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2018Group Normalizationcited by 1,514
  8. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  9. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  10. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  11. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  12. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
35 more
  1. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  2. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 360
  3. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  4. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
  5. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  6. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  7. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  8. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  9. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  10. 2019PointNetLK: Robust & Efficient Point Cloud Registration using PointNetcited by 231
  11. 2020Deep Global Registrationcited by 228
  12. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  13. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 170
  14. 20183D-CODED : 3D Correspondences by Deep Deformationcited by 160
  15. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  16. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  17. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  18. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  19. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  20. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  21. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  22. 2020se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domainscited by 87
  23. 2021CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Cloudscited by 83
  24. 2020Gradient Centralization: A New Optimization Technique for Deep Neural Networkscited by 82
  25. 20196-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypointscited by 78
  26. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  27. 2019PCRNet: Point Cloud Registration Network using PointNet Encodingcited by 63
  28. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  29. 2018Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimationcited by 51
  30. 2021Shape registration in the time of transformerscited by 51
  31. 2020G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Featurescited by 35
  32. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  33. 2021iCaps: Iterative Category-level Object Pose and Shape Estimationcited by 23
  34. 2021ACR-Pose: Adversarial Canonical Representation Reconstruction Network for Category Level 6D Object Pose Estimationcited by 20
  35. 2021CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Cloudscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 9; 2024: 7; 2025: 4; 2026: 7.

28 papers.

Sort:

By area:

  1. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  2. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  3. 2024Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Trackingcited by 48
  4. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  5. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 47
  6. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 40
  7. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  8. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  9. 2025Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimationcited by 16
  10. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 12
  11. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  12. 2024Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimationcited by 11
16 more
  1. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  2. 2023Get a Grip: Reconstructing Hand-Object Stable Grasps in Egocentric Videoscited by 10
  3. 2025CleanPose: Category-Level Object Pose Estimation via Causal Learning and Knowledge Distillationcited by 9
  4. 2023Depth-based 6DoF Object Pose Estimation using Swin Transformercited by 8
  5. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  6. 2024Street Gaussians without 3D Object Trackercited by 4
  7. 2025Category-Level Object Shape and Pose Estimation in Less Than a Millisecondcited by 2
  8. 2024Diffusion-Driven Self-Supervised Learning for Shape Reconstruction and Pose Estimationcited by 1
  9. 2023TransPose: A Transformer-based 6D Object Pose Estimation Network with Depth Refinementcited by 0
  10. 2026RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimationcited by 0
  11. 2026Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimationcited by 0
  12. 2026PCSTracker: Long-Term Scene Flow Estimation for Point Cloud Sequencescited by 0
  13. 2026TSM-Pose: Topology-Aware Learning with Semantic Mamba for Category-Level Object Pose Estimationcited by 0
  14. 2026ComPose: When to Trust Hands for Object Pose Trackingcited by 0
  15. 2026Symmetry-Aware 9D Pose Estimation with Sim(3)-Consistent Feature and Spherical Inception Convolutioncited by 0
  16. 2026GenCOPE: Syn2Real Generalized Category-Level Object Pose Estimation for Robotic Pickingcited by 0