mlsanityData to 7 Oct 2026

Neural Correspondence Field for Object Pose Estimation

arXiv 2208.00113 ↗First posted 30 Jul 2022cs.CV cs.AI cs.LGcited by 21

Not on the map. Why?

Abstract (arXiv)

We propose a method for estimating the 6DoF pose of a rigid object with an available 3D model from a single RGB image. Unlike classical correspondence-based methods which predict 3D object coordinates at pixels of the input image, the proposed method predicts 3D object coordinates at 3D query points sampled in the camera frustum. The move from pixels to 3D points, which is inspired by recent PIFu-style methods for 3D reconstruction, enables reasoning about the whole object, including its (self-)occluded parts. For a 3D query point associated with a pixel-aligned image feature, we train a fully-connected neural network to predict: (i) the corresponding 3D object coordinates, and (ii) the signed distance to the object surface, with the first defined only for query points in the surface vicinity. We call the mapping realized by this network as Neural Correspondence Field. The object pose is then robustly estimated from the predicted 3D-3D correspondences by the Kabsch-RANSAC algorithm. The proposed method achieves state-of-the-art results on three BOP datasets and is shown superior especially in challenging cases with occlusion. The project website is at: linhuang17.github.io/NCF.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 55 of its 84 references that are in the map. First posted on arXiv 30 Jul 2022.

Builds on

55 of 84 references.

References · 55

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  2. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  3. 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,459
  4. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  5. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  6. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  7. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  8. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  9. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  10. 2020Implicit Geometric Regularization for Learning Shapescited by 707
  11. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  12. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
38 more
  1. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  2. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  3. 2020Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Videocited by 470
  4. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 389
  5. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  6. 2021Advances in Neural Renderingcited by 365
  7. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 332
  8. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  9. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
  10. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  11. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  12. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  13. 2020PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstructioncited by 231
  14. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  15. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  16. 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
  17. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  18. 2019Texture Fields: Learning Texture Representations in Function Spacecited by 210
  19. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  20. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  21. 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 178
  22. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  23. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  24. 2017Graph-Cut RANSACcited by 133
  25. 2020Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondencecited by 119
  26. 2020SALD: Sign Agnostic Learning with Derivativescited by 115
  27. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  28. 20176-DoF Object Pose from Semantic Keypointscited by 89
  29. 2021NPMs: Neural Parametric Models for 3D Deformable Shapescited by 89
  30. 2020Articulation-aware Canonical Surface Mappingcited by 80
  31. 2020Continuous Surface Embeddingscited by 79
  32. 2019BlenderProccited by 76
  33. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  34. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  35. 2018A Unified Framework for Multi-View Multi-Class Object Pose Estimationcited by 49
  36. 2019Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithmcited by 43
  37. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  38. 2017Going Further with Point Pair Featurescited by 28

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 5; 2025: 3; 2026: 1.

21 papers.

Sort:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  3. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  4. 2024Distillation of Diffusion Features for Semantic Correspondencecited by 17
  5. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  6. 2023Rigidity-Aware Detection for 6D Object Pose Estimationcited by 13
  7. 2025Do It Yourself: Learning Semantic Correspondence from Pseudo-Labelscited by 13
  8. 2023SOCS: Semantically-aware Object Coordinate Space for Category-Level 6D Object Pose Estimation under Large Shape Variationscited by 12
  9. 2023iComMa: Inverting 3D Gaussian Splatting for Camera Pose Estimation via Comparing and Matchingcited by 12
  10. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  11. 2023Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objectscited by 9
  12. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
9 more
  1. 2024Semantically-aware Neural Radiance Fields for Visual Scene Understanding: A Comprehensive Reviewcited by 9
  2. 2022ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapescited by 6
  3. 2023Neural Voting Field for Camera-Space 3D Hand Pose Estimationcited by 6
  4. 2023Factored Neural Representation for Scene Understandingcited by 4
  5. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  6. 2024NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Modelscited by 2
  7. 2025RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Basecited by 0
  8. 2025Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perceptioncited by 0
  9. 2026Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimationcited by 0