# DeepAAT: Deep Automated Aerial Triangulation for Fast UAV-based Mapping

arXiv: https://arxiv.org/abs/2402.01134 · HTML: https://mlsanity.com/paper/2402.01134/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 2 Feb 2024.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [DeepSFM: Structure From Motion Via Deep Bundle Adjustment](https://mlsanity.com/paper/1912.09697/) (2019)
- [Deep Models of Interactions Across Sets](https://mlsanity.com/paper/1803.02879/) (2018)
- [Deep Two-View Structure-from-Motion Revisited](https://mlsanity.com/paper/2104.00556/) (2021)
- [A Review on Deep Learning in UAV Remote Sensing](https://mlsanity.com/paper/2101.10861/) (2021)
- [Graph-Based Parallel Large Scale Structure from Motion](https://mlsanity.com/paper/1912.10659/) (2019)
- [Deep Permutation Equivariant Structure from Motion](https://mlsanity.com/paper/2104.06703/) (2021)
- [Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set](https://mlsanity.com/paper/2206.11499/) (2022)
- [DRO: Deep Recurrent Optimizer for Video to Depth](https://mlsanity.com/paper/2103.13201/) (2021)
- [Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty](https://mlsanity.com/paper/2104.08278/) (2021)
- [DeepMLE: A Robust Deep Maximum Likelihood Estimator for Two-view Structure from Motion](https://mlsanity.com/paper/2210.05517/) (2022)
- [Parallel Structure from Motion from Local Increment to Global Averaging](https://mlsanity.com/paper/1702.08601/) (2017)

## Built on by (most cited first, 1 of 1)

- [Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion](https://mlsanity.com/paper/2609.09491/) (2026)

## Abstract (arXiv)

Automated Aerial Triangulation (AAT), aiming to restore image pose and reconstruct sparse points simultaneously, plays a pivotal role in earth observation. With its rich research heritage spanning several decades in photogrammetry, AAT has evolved into a fundamental process widely applied in large-scale Unmanned Aerial Vehicle (UAV) based mapping. Despite its advancements, classic AAT methods still face challenges like low efficiency and limited robustness. This paper introduces DeepAAT, a deep learning network designed specifically for AAT of UAV imagery. DeepAAT considers both spatial and spectral characteristics of imagery, enhancing its capability to resolve erroneous matching pairs and accurately predict image poses. DeepAAT marks a significant leap in AAT's efficiency, ensuring thorough scene coverage and precision. Its processing speed outpaces incremental AAT methods by hundreds of times and global AAT methods by tens of times while maintaining a comparable level of reconstruction accuracy. Additionally, DeepAAT's scene clustering and merging strategy facilitate rapid localization and pose determination for large-scale UAV images, even under constrained computing resources. The experimental results demonstrate DeepAAT's substantial improvements over conventional AAT methods, highlighting its potential in the efficiency and accuracy of UAV-based 3D reconstruction tasks. To benefit the photogrammetry society, the code of DeepAAT will be released at: https://github.com/WHU-USI3DV/DeepAAT.