mlsanityData to 14 Oct 2026

PicoPose: Progressive Pixel-to-Pixel Correspondence Learning for Novel Object Pose Estimation

arXiv 2504.02617 ↗First posted 3 Apr 2025cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

RGB-based novel object pose estimation is critical for rapid deployment in robotic applications, yet zero-shot generalization remains a key challenge. In this paper, we introduce PicoPose, a novel framework designed to tackle this task using a three-stage pixel-to-pixel correspondence learning process. Firstly, PicoPose matches features from the RGB observation with those from rendered object templates, identifying the best-matched template and establishing coarse correspondences. Secondly, PicoPose smooths the correspondences by globally regressing a 2D affine transformation, including in-plane rotation, scale, and 2D translation, from the coarse correspondence map. Thirdly, PicoPose applies the affine transformation to the feature map of the best-matched template and learns correspondence offsets within local regions to achieve fine-grained correspondences. By progressively refining the correspondences, PicoPose significantly improves the accuracy of object poses computed via PnP/RANSAC. PicoPose achieves state-of-the-art performance on the seven core datasets of the BOP benchmark, demonstrating exceptional generalization to novel objects. Code and trained models are available at https://github.com/foollh/PicoPose.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 39 of its 48 references that are in the map. First posted on arXiv 3 Apr 2025.

Builds on

39 of 48 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  9. 2021Vision Transformers for Dense Predictioncited by 1,803
  10. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  11. 2023Wonder3D: Single Image to 3D using Cross-Domain Diffusioncited by 689
  12. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
27 more
  1. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  2. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  3. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  4. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  5. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  6. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  7. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  8. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  9. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  10. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  11. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  12. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  13. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  14. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  15. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  16. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  17. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  18. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  19. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  20. 2023CNOS: A Strong Baseline for CAD-based Novel Object Segmentationcited by 87
  21. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  22. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 74
  23. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  24. 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
  25. 2023VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representationscited by 41
  26. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 33
  27. 2023SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objectscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2026Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agentscited by 4
  2. 2025Geo6DPose: Fast Zero-Shot 6D Object Pose Estimation via Geometry-Filtered Feature Matchingcited by 0
  3. 2026Robust PnP on a Neuromorphic Processor for Object Pose Estimationcited by 0
  4. 2026HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimationcited by 0
  5. 2026PICO: Projection-Informed Consistency Optimisation for 6DoF Surgical Tool Pose Estimationcited by 0
  6. 2026MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulationcited by 0