mlsanityData to 7 Oct 2026

3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation

arXiv 2310.03534 ↗First posted 5 Oct 2023cs.CV cs.ROcited by 11

Not on the map. Why?

Abstract (arXiv)

Prior methods that tackle the problem of generalizable object pose estimation highly rely on having dense views of the unseen object. By contrast, we address the scenario where only a single reference view of the object is available. Our goal then is to estimate the relative object pose between this reference view and a query image that depicts the object in a different pose. In this scenario, robust generalization is imperative due to the presence of unseen objects during testing and the large-scale object pose variation between the reference and the query. To this end, we present a new hypothesis-and-verification framework, in which we generate and evaluate multiple pose hypotheses, ultimately selecting the most reliable one as the relative object pose. To measure reliability, we introduce a 3D-aware verification that explicitly applies 3D transformations to the 3D object representations learned from the two input images. Our comprehensive experiments on the Objaverse, LINEMOD, and CO3D datasets evidence the superior accuracy of our approach in relative pose estimation and its robustness in large-scale pose variations, when dealing with unseen objects.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 40 of its 53 references that are in the map. First posted on arXiv 5 Oct 2023.

Builds on

40 of 53 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2023Segment Anythingcited by 8,158
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  7. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  10. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  11. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  12. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
28 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  3. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  4. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  5. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 352
  6. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  7. 2017Learning to Find Good Correspondencescited by 176
  8. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  9. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  10. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  11. 2020Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimationcited by 123
  12. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  13. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 115
  14. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  15. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  16. 2019Single-Stage 6D Object Pose Estimationcited by 88
  17. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 88
  18. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  19. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  20. 2023Siamese Masked Autoencoderscited by 75
  21. 2022Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networkscited by 73
  22. 2023Detecting Everything in the Open World: Towards Universal Object Detectioncited by 62
  23. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  24. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  25. 2021Progressive Correspondence Pruning by Consensus Learningcited by 46
  26. 2021Learning to Detect Every Thing in an Open Worldcited by 37
  27. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  28. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 4; 2026: 1.

11 papers.

  1. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  2. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  3. 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesiscited by 9
  4. 2023FocalPose++: Focal Length and Object Pose Estimation via Render and Comparecited by 3
  5. 2025Structure-Aware Correspondence Learning for Relative Pose Estimationcited by 3
  6. 2025BoxDreamer: Dreaming Box Corners for Generalizable Object Pose Estimationcited by 3
  7. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  8. 2025SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Referencecited by 1
  9. 2024DVMNet++: Rethinking Relative Pose Estimation for Unseen Objectscited by 0
  10. 2024Towards Human-Level 3D Relative Pose Estimation: Generalizable, Training-Free, with Single Referencecited by 0
  11. 2026Pose Anything Anywhere:Model-free Object Poses from Arbitrary Referencescited by 0