mlsanityData to 7 Oct 2026

MAPRPose: Mask-Aware Proposal and Amodal Refinement for Multi-Object 6D Pose Estimation

arXiv 2604.20650 ↗First posted 22 Apr 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework that leverages mask-aware correspondences for pose proposal and amodal-driven Region-of-Interest (ROI) prediction for robust refinement. In the Mask-Aware Pose Proposal (MAPP) stage, we lift 2D correspondences into 3D space to establish reliable keypoint matches and generate geometrically consistent pose hypotheses based on correspondence-level scoring, from which the top-K candidates are selected. In the refinement stage, we introduce a tensorized render-and-compare pipeline integrated with an Amodal Mask Prediction and ROI Re-Alignment (AMPR) module. By reconstructing complete object geometry and dynamically adjusting the ROI, AMPR mitigates localization errors and spatial misalignment under heavy occlusion. Furthermore, our GPU-accelerated RGB-XYZ reprojection enables simultaneous refinement of all N × B pose hypotheses in a single forward pass.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 75 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

44 of 75 references.

References · 44

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  2. 2017Mask R-CNNcited by 7,259
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  4. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  5. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  6. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  7. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  8. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  9. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  10. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  11. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  12. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
32 more
  1. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  2. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  3. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  4. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
  5. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  6. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 115
  7. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  8. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 113
  9. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  10. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  11. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  12. 2021SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimationcited by 88
  13. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  14. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 56
  15. 2025Amodal3R: Amodal 3D Reconstruction from Occluded 2D Imagescited by 52
  16. 2025Any6D: Model-free 6D Pose Estimation of Novel Objectscited by 47
  17. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  18. 2022Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimationcited by 34
  19. 2023Open-vocabulary object 6D pose estimationcited by 29
  20. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  21. 2023Boosting Video Object Segmentation via Space-time Correspondence Learningcited by 21
  22. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  23. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
  24. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
  25. 2025Co-op: Correspondence-based Novel Object Pose Estimationcited by 13
  26. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  27. 2025UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial Referencescited by 9
  28. 20196D Pose Estimation with Correlation Fusioncited by 6
  29. 2025DynamicPose: Real-time and Robust 6D Object Pose Tracking for Fast-Moving Cameras and Objectscited by 5
  30. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  31. 2023Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identificationcited by 2
  32. 2025ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulationcited by 1

Built on by

Not cited yet.