mlsanityData to 14 Oct 2026

Occlusion-Robust Object Pose Estimation with Holistic Representation

arXiv 2110.11636 ↗First posted 22 Oct 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Practical object pose estimation demands robustness against occlusions to the target object. State-of-the-art (SOTA) object pose estimators take a two-stage approach, where the first stage predicts 2D landmarks using a deep network and the second stage solves for 6DOF pose from 2D-3D correspondences. Albeit widely adopted, such two-stage approaches could suffer from novel occlusions when generalising and weak landmark coherence due to disrupted features. To address these issues, we develop a novel occlude-and-blackout batch augmentation technique to learn occlusion-robust deep features, and a multi-precision supervision architecture to encourage holistic pose representation learning for accurate and coherent landmark predictions. We perform careful ablation tests to verify the impact of our innovations and compare our method to SOTA pose estimators. Without the need of any post-processing or refinement, our method exhibits superior performance on the LINEMOD dataset. On the YCB-Video dataset our method outperforms all non-refinement methods in terms of the ADD(-S) metric. We also demonstrate the high data-efficiency of our method. Our code is available at http://github.com/BoChenYS/ROPE

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

41 of 65 references.

References · 41

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2017Mask R-CNNcited by 7,277
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  5. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2017Random Erasing Data Augmentationcited by 1,239
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  9. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  10. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  11. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
  12. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
29 more
  1. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  2. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  3. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  4. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  5. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  6. 2017Real-Time Seamless Single Shot 6D Object Pose Predictioncited by 210
  7. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  8. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  9. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  10. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  11. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  12. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  13. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  14. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  15. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  16. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  17. 20176-DoF Object Pose from Semantic Keypointscited by 89
  18. 2019Single-Stage 6D Object Pose Estimationcited by 88
  19. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  20. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  21. 2018Deep Model-Based 6D Pose Refinement in RGBcited by 59
  22. 2019Satellite Pose Estimation with Deep Landmark Regression and Nonlinear Pose Refinementcited by 56
  23. 2019Multi-path Learning for Object Pose Estimation Across Domainscited by 52
  24. 2018Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networkscited by 34
  25. 2018Deep-6DPose: Recovering 6D Object Pose from a Single RGB Imagecited by 26
  26. 2016Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsingcited by 19
  27. 2018CRAVES: Controlling Robotic Arm with a Vision-based Economic Systemcited by 18
  28. 2016Global Hypothesis Generation for 6D Object Pose Estimationcited by 17
  29. 2016Fast Single Shot Detection and Pose Estimationcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

6 papers.

  1. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  2. 2024Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularizationcited by 7
  3. 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6
  4. 2025HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimationcited by 3
  5. 2025Linear time small coresets for k-mean clustering of segments with applicationscited by 0
  6. 2026Robust PnP on a Neuromorphic Processor for Object Pose Estimationcited by 0