mlsanityData to 14 Oct 2026

UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image

arXiv 2411.16106 ↗First posted 25 Nov 2024cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Unseen object pose estimation methods often rely on CAD models or multiple reference views, making the onboarding stage costly. To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D reference image. While previous works leverage reference images as pose anchors to limit the range of relative pose, our scenario presents significant challenges since the relative transformation could vary across the entire SE(3) space. Moreover, factors like occlusion, sensor noise, and extreme geometry could result in low viewpoint overlap. To address these challenges, we present a novel approach and benchmark, termed UNOPose, for unseen one-reference-based object pose estimation. Building upon a coarse-to-fine paradigm, UNOPose constructs an SE(3)-invariant reference frame to standardize object representation despite pose and size variations. To alleviate small overlap across viewpoints, we recalibrate the weight of each correspondence based on its predicted likelihood of being within the overlapping region. Evaluated on our proposed benchmark based on the BOP Challenge, UNOPose demonstrates superior performance, significantly outperforming traditional and learning-based methods in the one-reference setting and remaining competitive with CAD-model-based methods. The code and dataset are available at https://github.com/shanice-l/UNOPose.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 93 of its 115 references that are in the map. First posted on arXiv 25 Nov 2024.

Builds on

93 of 115 references.

References · 93

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  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. 2017Mask R-CNNcited by 7,277
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  9. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  10. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
  12. 2023Vision Transformers Need Registerscited by 871
38 more
  1. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  2. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  3. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  4. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  5. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  6. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  7. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  8. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 321
  9. 2020PREDATOR: Registration of 3D Point Clouds with Low Overlapcited by 290
  10. 2023Fast Segment Anythingcited by 290
  11. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  12. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  13. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 258
  14. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  15. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 241
  16. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  17. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  18. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  19. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 172
  20. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 161
  21. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  22. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  23. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  24. 2021PointDSC: Robust Point Cloud Registration using Deep Spatial Consistencycited by 142
  25. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  26. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 124
  27. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  28. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 121
  29. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  30. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 115
  31. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  32. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  33. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  34. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
  35. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  36. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  37. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  38. 2019Single-Stage 6D Object Pose Estimationcited by 88

50 most cited of 93 All 93 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 6; 2026: 5.

12 papers.

  1. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 49
  2. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 38
  3. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  4. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  5. 2025ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectorscited by 5
  6. 2024Street Gaussians without 3D Object Trackercited by 4
  7. 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimationcited by 2
  8. 2026COG: Confidence-aware Optimal Geometric Correspondence for Unsupervised Single-reference Novel Object Pose Estimationcited by 1
  9. 2026Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimationcited by 1
  10. 2026RAVA: Retrieval-Augmented Viewpoint Alignment for Subject-Driven Image Generationcited by 0
  11. 2026Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimationcited by 0
  12. 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videoscited by 0