# A Structure-Aware Method for Direct Pose Estimation

arXiv: https://arxiv.org/abs/2012.12360 · HTML: https://mlsanity.com/paper/2012.12360/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras](https://mlsanity.com/paper/2312.00500/) (2023)
- [GRLoc: Geometric Representation Regression for Visual Localization](https://mlsanity.com/paper/2511.13864/) (2025)
- [Implicit Learning of Scene Geometry from Poses for Global Localization](https://mlsanity.com/paper/2312.02029/) (2023)

## Abstract (arXiv)

Estimating camera pose from a single image is a fundamental problem in computer vision. Existing methods for solving this task fall into two distinct categories, which we refer to as direct and indirect. Direct methods, such as PoseNet, regress pose from the image as a fixed function, for example using a feed-forward convolutional network. Such methods are desirable because they are deterministic and run in constant time. Indirect methods for pose regression are often non-deterministic, with various external dependencies such as image retrieval and hypothesis sampling. We propose a direct method that takes inspiration from structure-based approaches to incorporate explicit 3D constraints into the network. Our approach maintains the desirable qualities of other direct methods while achieving much lower error in general.