mlsanityData to 14 Oct 2026

COPE: End-to-end trainable Constant Runtime Object Pose Estimation

arXiv 2208.08807 ↗First posted 18 Aug 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction as a second stage. Poses are subsequently estimated using the Perspective-n-Points algorithm at runtime. Unfortunately, multi-model formulations are slow and do not scale well with the number of object instances involved. Recent approaches show that direct 6D object pose estimation is feasible when derived from the aforementioned geometric correspondences. We present an approach that learns an intermediate geometric representation of multiple objects to directly regress 6D poses of all instances in a test image. The inherent end-to-end trainability overcomes the requirement of separately processing individual object instances. By calculating the mutual Intersection-over-Unions, pose hypotheses are clustered into distinct instances, which achieves negligible runtime overhead with respect to the number of object instances. Results on multiple challenging standard datasets show that the pose estimation performance is superior to single-model state-of-the-art approaches despite being more than ~35 times faster. We additionally provide an analysis showing real-time applicability (>24 fps) for images where more than 90 object instances are present. Further results show the advantage of supervising geometric-correspondence-based object pose estimation with the 6D pose.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 45 of its 62 references that are in the map. First posted on arXiv 18 Aug 2022.

Builds on

45 of 62 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2017Mask R-CNNcited by 7,277
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
  10. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  11. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  12. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
33 more
  1. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  2. 2017Focal Loss for Dense Object Detectioncited by 752
  3. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  4. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
  5. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  6. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  7. 2020BOP Challenge 2020 on 6D Object Localizationcited by 193
  8. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  9. 2020Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Imagecited by 172
  10. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  11. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  12. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  13. 2017Graph-Cut RANSACcited by 133
  14. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  15. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  16. 2018Segmentation-driven 6D Object Pose Estimationcited by 104
  17. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  18. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  19. 2019Single-Stage 6D Object Pose Estimationcited by 88
  20. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  21. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  22. 2020Self6D: Self-Supervised Monocular 6D Object Pose Estimationcited by 79
  23. 2018Making Deep Heatmaps Robust to Partial Occlusions for 3D Object Pose Estimationcited by 74
  24. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  25. 2019Photorealistic Image Synthesis for Object Instance Detectioncited by 66
  26. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  27. 2017On Pre-Trained Image Features and Synthetic Images for Deep Learningcited by 51
  28. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  29. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  30. 2021StablePose: Learning 6D Object Poses from Geometrically Stable Patchescited by 17
  31. 2020MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervisioncited by 16
  32. 2020PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shiftcited by 14
  33. 2020DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-based Robotic Graspingcited by 11

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 5; 2024: 2; 2025: 2.

10 papers.

  1. 2023ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformerscited by 45
  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. 2023Self-supervised Vision Transformers for 3D Pose Estimation of Novel Objectscited by 9
  5. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 4
  6. 2023Open Challenges for Monocular Single-shot 6D Object Pose Estimationcited by 2
  7. 2024Shape-biased Texture Agnostic Representations for Improved Textureless and Metallic Object Detection and 6D Pose Estimationcited by 2
  8. 2022Grasping the Inconspicuouscited by 1
  9. 2025Parallel Sampling of Diffusion Models on SO(3)cited by 1
  10. 2024Sparse Color-Code Net: Real-Time RGB-Based 6D Object Pose Estimation on Edge Devicescited by 0