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

arXiv: https://arxiv.org/abs/1906.05105 · HTML: https://mlsanity.com/paper/1906.05105/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 30 of 39)

- [MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare](https://mlsanity.com/paper/2212.06870/) (2022)
- [NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild](https://mlsanity.com/paper/2110.07604/) (2021)
- [Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images](https://mlsanity.com/paper/2204.10776/) (2022)
- [FoundPose: Unseen Object Pose Estimation with Foundation Features](https://mlsanity.com/paper/2311.18809/) (2023)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [RelPose++: Recovering 6D Poses from Sparse-view Observations](https://mlsanity.com/paper/2305.04926/) (2023)
- [FS6D: Few-Shot 6D Pose Estimation of Novel Objects](https://mlsanity.com/paper/2203.14628/) (2022)
- [OSOP: A Multi-Stage One Shot Object Pose Estimation Framework](https://mlsanity.com/paper/2203.15533/) (2022)
- [Zero-Shot Category-Level Object Pose Estimation](https://mlsanity.com/paper/2204.03635/) (2022)
- [Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions](https://mlsanity.com/paper/2203.17234/) (2022)
- [NOPE: Novel Object Pose Estimation from a Single Image](https://mlsanity.com/paper/2303.13612/) (2023)
- [GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects](https://mlsanity.com/paper/2403.11510/) (2024)
- [POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Reference](https://mlsanity.com/paper/2305.15727/) (2023)
- [ZePHyR: Zero-shot Pose Hypothesis Rating](https://mlsanity.com/paper/2104.13526/) (2021)
- [ODAM: Object Detection, Association, and Mapping using Posed RGB Video](https://mlsanity.com/paper/2108.10165/) (2021)
- [IKEA-Manual: Seeing Shape Assembly Step by Step](https://mlsanity.com/paper/2302.01881/) (2023)
- [PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning](https://mlsanity.com/paper/2105.05643/) (2021)
- [Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images](https://mlsanity.com/paper/2306.07598/) (2023)
- [Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transforms](https://mlsanity.com/paper/2105.14246/) (2021)
- [Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects](https://mlsanity.com/paper/2203.08472/) (2022)
- [Translating a Visual LEGO Manual to a Machine-Executable Plan](https://mlsanity.com/paper/2207.12572/) (2022)
- [A step towards understanding why classification helps regression](https://mlsanity.com/paper/2308.10603/) (2023)
- [GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting](https://mlsanity.com/paper/2403.10683/) (2024)
- [PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching](https://mlsanity.com/paper/2304.01382/) (2023)
- [LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation](https://mlsanity.com/paper/2211.16290/) (2022)
- [OSSID: Online Self-Supervised Instance Detection by (and for) Pose Estimation](https://mlsanity.com/paper/2201.07309/) (2022)
- [You Only Look at One: Category-Level Object Representations for Pose Estimation From a Single Example](https://mlsanity.com/paper/2305.12626/) (2023)
- [RoSI: Recovering 3D Shape Interiors from Few Articulation Images](https://mlsanity.com/paper/2304.06342/) (2023)
- [Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos](https://mlsanity.com/paper/2407.04384/) (2024)
- [Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimation](https://mlsanity.com/paper/2311.09500/) (2023)

## 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.