# AEPnP: A Less-constrained EPnP Solver for Pose Estimation with Anisotropic Scaling

arXiv: https://arxiv.org/abs/2310.09982 · HTML: https://mlsanity.com/paper/2310.09982/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 44 references that are in the map.
- First posted on arXiv 15 Oct 2023.

## Builds on (most cited first, 5 of 5)

- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations](https://mlsanity.com/paper/2002.12687/) (2020)
- [An Efficient Algebraic Solution to the Perspective-Three-Point Problem](https://mlsanity.com/paper/1701.08237/) (2017)
- [Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem](https://mlsanity.com/paper/2003.06752/) (2020)

## Abstract (arXiv)

Perspective-n-Point (PnP) stands as a fundamental algorithm for pose estimation in various applications. In this paper, we present a new approach to the PnP problem with relaxed constraints, eliminating the need for precise 3D coordinates, which is especially suitable for object pose estimation where corresponding object models may not be available in practice. Built upon the classical EPnP solver, we refer to it as AEPnP due to its ability to handle unknown anisotropic scaling factors in addition to the common 6D transformation. Through a few algebraic manipulations and a well-chosen frame of reference, this new problem can be boiled down to a simple linear null-space problem followed by point registration-based identification of a similarity transformation. Experimental results on both simulated and real datasets demonstrate the effectiveness of AEPnP as a flexible and practical solution to object pose estimation. Code: https://github.com/goldoak/AEPnP.