mlsanityData to 7 Oct 2026

RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery

arXiv 2309.10255 ↗First posted 19 Sep 2023cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

While showing promising results, recent RGB-D camera-based category-level object pose estimation methods have restricted applications due to the heavy reliance on depth sensors. RGB-only methods provide an alternative to this problem yet suffer from inherent scale ambiguity stemming from monocular observations. In this paper, we propose a novel pipeline that decouples the 6D pose and size estimation to mitigate the influence of imperfect scales on rigid transformations. Specifically, we leverage a pre-trained monocular estimator to extract local geometric information, mainly facilitating the search for inlier 2D-3D correspondence. Meanwhile, a separate branch is designed to directly recover the metric scale of the object based on category-level statistics. Finally, we advocate using the RANSAC-PnP algorithm to robustly solve for 6D object pose. Extensive experiments have been conducted on both synthetic and real datasets, demonstrating the superior performance of our method over previous state-of-the-art RGB-based approaches, especially in terms of rotation accuracy. Code: https://github.com/goldoak/DMSR.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 24 of its 38 references that are in the map. First posted on arXiv 19 Sep 2023.

Builds on

24 of 38 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2016Pyramid Scene Parsing Networkcited by 2,472
  5. 2021Vision Transformers for Dense Predictioncited by 1,789
  6. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  7. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  8. 2020Shape Prior Deformation for Categorical 6D Object Pose and Size Estimationcited by 158
  9. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  10. 2021FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanismcited by 121
  11. 20223D Common Corruptions and Data Augmentationcited by 120
  12. 2021DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistencycited by 103
12 more
  1. 2020Category Level Object Pose Estimation via Neural Analysis-by-Synthesiscited by 100
  2. 2022GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Votingcited by 94
  3. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  4. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  5. 2021RePOSE: Fast 6D Object Pose Refinement via Deep Texture Renderingcited by 63
  6. 2021SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimationcited by 53
  7. 2021Category-Level Metric Scale Object Shape and Pose Estimationcited by 40
  8. 2022RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimizationcited by 38
  9. 2022Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Imagecited by 29
  10. 2019Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Reviewcited by 12
  11. 20176D Object Pose Estimation with Depth Images: A Seamless Approach for Robotic Interaction and Augmented Realitycited by 6
  12. 2023RGB-D-Based Categorical Object Pose and Shape Estimation: Methods, Datasets, and Evaluationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  2. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  3. 2024LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimationcited by 13
  4. 2025Orientation Matters: Making 3D Generative Models Orientation-Alignedcited by 13
  5. 2025GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimationcited by 5
  6. 2025MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Modelcited by 4
  7. 2025Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypescited by 3
  8. 2025You Only Pose Once: A Minimalist's Detection Transformer for Monocular RGB Category-level 9D Multi-Object Pose Estimationcited by 1
  9. 2024Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusioncited by 0
  10. 2025PoseIDON: 6DoF Pose Estimation with Foundation Model Features for Marine Sediment Burial Mappingcited by 0
  11. 2025RCGNet: RGB-based Category-Level 6D Object Pose Estimation with Geometric Guidancecited by 0
  12. 2026Object Pose Transformer: Unifying Unseen Object Pose Estimationcited by 0
1 more
  1. 2026Emergence of a Shared Canonical Object Frame from In-the-Wild Videoscited by 0