mlsanityData to 7 Oct 2026

SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation

arXiv 2108.08367 ↗First posted 18 Aug 2021cs.CVcited by 88

Not on the map. Why?

Abstract (arXiv)

Directly regressing all 6 degrees-of-freedom (6DoF) for the object pose (e.g. the 3D rotation and translation) in a cluttered environment from a single RGB image is a challenging problem. While end-to-end methods have recently demonstrated promising results at high efficiency, they are still inferior when compared with elaborate PnP/RANSAC-based approaches in terms of pose accuracy. In this work, we address this shortcoming by means of a novel reasoning about self-occlusion, in order to establish a two-layer representation for 3D objects which considerably enhances the accuracy of end-to-end 6D pose estimation. Our framework, named SO-Pose, takes a single RGB image as input and respectively generates 2D-3D correspondences as well as self-occlusion information harnessing a shared encoder and two separate decoders. Both outputs are then fused to directly regress the 6DoF pose parameters. Incorporating cross-layer consistencies that align correspondences, self-occlusion and 6D pose, we can further improve accuracy and robustness, surpassing or rivaling all other state-of-the-art approaches on various challenging datasets.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 18 Aug 2021.

Builds on

35 of 49 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  5. 2018YOLOv3: An Incremental Improvementcited by 2,652
  6. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  7. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  8. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  9. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  10. 2020ResNeSt: Split-Attention Networkscited by 445
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2019Lookahead Optimizer: k steps forward, 1 step backcited by 333
23 more
  1. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  2. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  3. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  4. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  5. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  6. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  7. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  8. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  9. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  10. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  11. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  12. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  13. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  14. 2019Single-Stage 6D Object Pose Estimationcited by 88
  15. 2020Gradient Centralization: A New Optimization Technique for Deep Neural Networkscited by 82
  16. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  17. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  18. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  19. 2015Learning Descriptors for Object Recognition and 3D Pose Estimationcited by 60
  20. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  21. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  22. 2016Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimationcited by 34
  23. 20183D Pose Estimation and 3D Model Retrieval for Objects in the Wildcited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 18; 2023: 30; 2024: 20; 2025: 9; 2026: 8.

88 papers.

Sort:

By area:

  1. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  2. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  3. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  4. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  5. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  6. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  7. 2023SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimationcited by 52
  8. 2022RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimationcited by 43
  9. 2022SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimationcited by 41
  10. 2024Instance-Adaptive and Geometric-Aware Keypoint Learning for Category-Level 6D Object Pose Estimationcited by 41
  11. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  12. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
38 more
  1. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  2. 2024Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformercited by 29
  3. 2023SG-Bot: Object Rearrangement via Coarse-to-Fine Robotic Imagination on Scene Graphscited by 24
  4. 20236D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimationcited by 24
  5. 2022TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimationcited by 23
  6. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  7. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  8. 2022Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Pickingcited by 20
  9. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  10. 2022SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimationcited by 17
  11. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  12. 2023Shape-Constraint Recurrent Flow for 6D Object Pose Estimationcited by 17
  13. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  14. 2021Polarimetric Pose Predictioncited by 16
  15. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 16
  16. 2022CRT-6D: Fast 6D Object Pose Estimation with Cascaded Refinement Transformerscited by 15
  17. 2023CheckerPose: Progressive Dense Keypoint Localization for Object Pose Estimation with Graph Neural Networkcited by 15
  18. 2023Rigidity-Aware Detection for 6D Object Pose Estimationcited by 13
  19. 2024LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimationcited by 13
  20. 2022DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimationcited by 12
  21. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  22. 2023MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervisioncited by 12
  23. 2024MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlationcited by 11
  24. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  25. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  26. 2024RHOBIN Challenge: Reconstruction of Human Object Interactioncited by 10
  27. 2024PEAR: Phrase-Based Hand-Object Interaction Anticipationcited by 10
  28. 2021DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimationcited by 9
  29. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictionscited by 9
  30. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  31. 2022Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimationcited by 7
  32. 2023Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimationcited by 7
  33. 2023TransPose: 6D Object Pose Estimation with Geometry-Aware Transformercited by 7
  34. 2023ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformationcited by 7
  35. 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6
  36. 2024KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformationcited by 6
  37. 2023DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimationcited by 5
  38. 2024Extending 6D Object Pose Estimators for Stereo Visioncited by 5

50 most cited of 88 All 88 (JSON)