# Ki-Pode: Keypoint-based Implicit Pose Distribution Estimation of Rigid Objects

arXiv: https://arxiv.org/abs/2209.09659 · HTML: https://mlsanity.com/paper/2209.09659/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 20 Sep 2022.

## Builds on (most cited first, 14 of 14)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [BOP Challenge 2020 on 6D Object Localization](https://mlsanity.com/paper/2009.07378/) (2020)
- [Implicit 3D Orientation Learning for 6D Object Detection from RGB Images](https://mlsanity.com/paper/1902.01275/) (2019)
- [Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views](https://mlsanity.com/paper/1505.05641/) (2015)
- [PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking](https://mlsanity.com/paper/1905.09304/) (2019)
- [Numerical Coordinate Regression with Convolutional Neural Networks](https://mlsanity.com/paper/1801.07372/) (2018)
- [Explaining the Ambiguity of Object Detection and 6D Pose From Visual Data](https://mlsanity.com/paper/1812.00287/) (2018)
- [Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold](https://mlsanity.com/paper/2106.05965/) (2021)
- [Deep Directional Statistics: Pose Estimation with Uncertainty Quantification](https://mlsanity.com/paper/1805.03430/) (2018)
- [Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation](https://mlsanity.com/paper/2012.11002/) (2020)
- [Probabilistic orientation estimation with matrix Fisher distributions](https://mlsanity.com/paper/2006.09740/) (2020)
- [Learning Orientation Distributions for Object Pose Estimation](https://mlsanity.com/paper/2007.01418/) (2020)
- [Fast Uncertainty Quantification for Deep Object Pose Estimation](https://mlsanity.com/paper/2011.07748/) (2020)

## Built on by (most cited first, 7 of 7)

- [MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images](https://mlsanity.com/paper/2403.01517/) (2024)
- [SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimation](https://mlsanity.com/paper/2303.05308/) (2023)
- [Multi-view object pose estimation from correspondence distributions and epipolar geometry](https://mlsanity.com/paper/2210.00924/) (2022)
- [BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguities](https://mlsanity.com/paper/2408.17297/) (2024)
- [Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributions](https://mlsanity.com/paper/2505.02501/) (2025)
- [Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Clouds](https://mlsanity.com/paper/2512.07211/) (2025)
- [Towards a Modular Bin-picking Framework for Handling Object Pose Uncertainties](https://mlsanity.com/paper/2607.13698/) (2026)

## Abstract (arXiv)

The estimation of 6D poses of rigid objects is a fundamental problem in computer vision. Traditionally pose estimation is concerned with the determination of a single best estimate. However, a single estimate is unable to express visual ambiguity, which in many cases is unavoidable due to object symmetries or occlusion of identifying features. Inability to account for ambiguities in pose can lead to failure in subsequent methods, which is unacceptable when the cost of failure is high. Estimates of full pose distributions are, contrary to single estimates, well suited for expressing uncertainty on pose. Motivated by this, we propose a novel pose distribution estimation method. An implicit formulation of the probability distribution over object pose is derived from an intermediary representation of an object as a set of keypoints. This ensures that the pose distribution estimates have a high level of interpretability. Furthermore, our method is based on conservative approximations, which leads to reliable estimates. The method has been evaluated on the task of rotation distribution estimation on the YCB-V and T-LESS datasets and performs reliably on all objects.