mlsanityData to 7 Oct 2026

SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddings

arXiv 2111.13489 ↗First posted 26 Nov 2021cs.CV cs.AI cs.LGcited by 95

Not on the map. Why?

Abstract (arXiv)

We present an approach to learn dense, continuous 2D-3D correspondence distributions over the surface of objects from data with no prior knowledge of visual ambiguities like symmetry. We also present a new method for 6D pose estimation of rigid objects using the learnt distributions to sample, score and refine pose hypotheses. The correspondence distributions are learnt with a contrastive loss, represented in object-specific latent spaces by an encoder-decoder query model and a small fully connected key model. Our method is unsupervised with respect to visual ambiguities, yet we show that the query- and key models learn to represent accurate multi-modal surface distributions. Our pose estimation method improves the state-of-the-art significantly on the comprehensive BOP Challenge, trained purely on synthetic data, even compared with methods trained on real data. The project site is at https://surfemb.github.io/ .

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

27 of 37 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,214
  7. 2018On the Spectral Bias of Neural Networkscited by 1,321
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  9. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  10. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  11. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  12. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
15 more
  1. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  2. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  3. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  4. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  5. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  6. 2018Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulationcited by 140
  7. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  8. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  9. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  10. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  11. 2020Continuous Surface Embeddingscited by 79
  12. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  13. 2017An Efficient Algebraic Solution to the Perspective-Three-Point Problemcited by 29
  14. 20203D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddingscited by 22
  15. 2020A Hybrid Approach for 6DoF Pose Estimationcited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 12; 2023: 26; 2024: 21; 2025: 22; 2026: 14.

95 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  3. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 142
  4. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  5. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  6. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  7. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  8. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  9. 2022Parallel Inversion of Neural Radiance Fields for Robust Pose Estimationcited by 55
  10. 2023HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimationcited by 47
  11. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  12. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
38 more
  1. 2023Open-vocabulary object 6D pose estimationcited by 29
  2. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  3. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  4. 2024UniGarmentManip: A Unified Framework for Category-Level Garment Manipulation via Dense Visual Correspondencecited by 22
  5. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  6. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  7. 2022StereoPose: Category-Level 6D Transparent Object Pose Estimation from Stereo Images via Back-View NOCScited by 18
  8. 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
  9. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  10. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  11. 2025CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-Worldcited by 16
  12. 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
  13. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  14. 2023SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimationcited by 14
  15. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
  16. 2023Rigidity-Aware Detection for 6D Object Pose Estimationcited by 13
  17. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
  18. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  19. 2024Object Pose Estimation via the Aggregation of Diffusion Featurescited by 12
  20. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  21. 2023Diff-DOPE: Differentiable Deep Object Pose Estimationcited by 11
  22. 2023PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environmentscited by 11
  23. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  24. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  25. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  26. 2025TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulationcited by 9
  27. 2024GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinementcited by 8
  28. 2023Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimationcited by 7
  29. 2025SurgRIPE challenge: Benchmark of Surgical Robot Instrument Pose Estimationcited by 7
  30. 2025XYZ-IBD: Benchmarking Robust 6D Object Pose Estimation under Real-World Industrial Complexitycited by 7
  31. 2022Ambiguity-Aware Multi-Object Pose Optimization for Visually-Assisted Robot Manipulationcited by 6
  32. 2022CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregationcited by 6
  33. 2024RayEmb: Arbitrary Landmark Detection in X-Ray Images Using Ray Embedding Subspacecited by 6
  34. 2022Multi-view object pose estimation from correspondence distributions and epipolar geometrycited by 5
  35. 20233D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose Estimationcited by 5
  36. 2023Exploring Shape Embedding for Cloth-Changing Person Re-Identification via 2D-3D Correspondencescited by 5
  37. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 5
  38. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4

50 most cited of 95 All 95 (JSON)