mlsanityData to 7 Oct 2026

Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objects

arXiv 1906.05105 ↗First posted 12 Jun 2019cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose. We believe this is a crucial step to design robotic systems that can interact with new objects in the wild not belonging to a predefined category. Our main insight is to dynamically condition pose estimation with a representation of the 3D shape of the target object. More precisely, we train a Convolutional Neural Network that takes as input both a test image and a 3D model, and outputs the relative 3D pose of the object in the input image with respect to the 3D model. We demonstrate that our method boosts performances for supervised category pose estimation on standard benchmarks, namely Pascal3D+, ObjectNet3D and Pix3D, on which we provide results superior to the state of the art. More importantly, we show that our network trained on everyday man-made objects from ShapeNet generalizes without any additional training to completely new types of 3D objects by providing results on the LINEMOD dataset as well as on natural entities such as animals from ImageNet.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 14; 2023: 13; 2024: 5.

39 papers.

Sort:

By area:

  1. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  2. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  3. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  4. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  5. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  6. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  7. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  8. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  9. 2022Zero-Shot Category-Level Object Pose Estimationcited by 57
  10. 2022Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusionscited by 54
  11. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  12. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
27 more
  1. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  2. 2021ZePHyR: Zero-shot Pose Hypothesis Ratingcited by 26
  3. 2021ODAM: Object Detection, Association, and Mapping using Posed RGB Videocited by 22
  4. 2023IKEA-Manual: Seeing Shape Assembly Step by Stepcited by 22
  5. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19
  6. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  7. 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transformscited by 17
  8. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  9. 2022Translating a Visual LEGO Manual to a Machine-Executable Plancited by 15
  10. 2023A step towards understanding why classification helps regressioncited by 15
  11. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
  12. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  13. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9
  14. 2022OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimationcited by 8
  15. 2023You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Examplecited by 8
  16. 2023RoSI: Recovering 3D Shape Interiors from Few Articulation Imagescited by 6
  17. 2024Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videoscited by 5
  18. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  19. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  20. 20223D-Augmented Contrastive Knowledge Distillation for Image-based Object Pose Estimationcited by 2
  21. 2022Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentationcited by 2
  22. 2023CA2T-Net: Category-Agnostic 3D Articulation Transfer from Single Imagecited by 2
  23. 2023Shape-Net: Room Layout Estimation from Panoramic Images Robust to Occlusion using Knowledge Distillation with 3D Shapes as Additional Inputscited by 2
  24. 2021Deep 6-DoF Tracking of Unknown Objects for Reactive Graspingcited by 1
  25. 2022Accidental Turntables: Learning 3D Pose by Watching Objects Turncited by 1
  26. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  27. 2021Geometric Change Detection in Digital Twins using 3D Machine Learningcited by 0