# Single View Geocentric Pose in the Wild

arXiv: https://arxiv.org/abs/2105.08229 · HTML: https://mlsanity.com/paper/2105.08229/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 18 May 2021.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images](https://mlsanity.com/paper/1805.06561/) (2018)
- [Learning Rich Features from RGB-D Images for Object Detection and Segmentation](https://mlsanity.com/paper/1407.5736/) (2014)
- [Depth-aware CNN for RGB-D Segmentation](https://mlsanity.com/paper/1803.06791/) (2018)
- [Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation](https://mlsanity.com/paper/1904.01870/) (2019)
- [Semantic Stereo for Incidental Satellite Images](https://mlsanity.com/paper/1811.08739/) (2018)
- [IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Network](https://mlsanity.com/paper/1802.10249/) (2018)
- [SpaceNet MVOI: a Multi-View Overhead Imagery Dataset](https://mlsanity.com/paper/1903.12239/) (2019)
- [Leveraging Vision Reconstruction Pipelines for Satellite Imagery](https://mlsanity.com/paper/1910.02989/) (2019)
- [RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter](https://mlsanity.com/paper/1810.00818/) (2018)
- [Learning Geocentric Object Pose in Oblique Monocular Images](https://mlsanity.com/paper/2007.00729/) (2020)
- [From Satellite Imagery to Disaster Insights](https://mlsanity.com/paper/1812.07033/) (2018)
- [AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotations](https://mlsanity.com/paper/1908.05263/) (2019)

## Built on by (most cited first, 9 of 9)

- [3D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisions](https://mlsanity.com/paper/2404.04823/) (2024)
- [SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery](https://mlsanity.com/paper/2406.18151/) (2024)
- [THE Benchmark: Transferable Representation Learning for Monocular Height Estimation](https://mlsanity.com/paper/2112.14985/) (2021)
- [HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images](https://mlsanity.com/paper/2309.16486/) (2023)
- [Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision](https://mlsanity.com/paper/2502.08352/) (2025)
- [Disentangled Latent Transformer for Interpretable Monocular Height Estimation](https://mlsanity.com/paper/2201.06357/) (2022)
- [Handling Image and Label Resolution Mismatch in Remote Sensing](https://mlsanity.com/paper/2211.15790/) (2022)
- [A Deep Learning Ensemble Framework for Off-Nadir Geocentric Pose Prediction](https://mlsanity.com/paper/2205.11230/) (2022)
- [Impact of architecture on robustness and interpretability of multispectral deep neural networks](https://mlsanity.com/paper/2309.12463/) (2023)

## Abstract (arXiv)

Current methods for Earth observation tasks such as semantic mapping, map alignment, and change detection rely on near-nadir images; however, often the first available images in response to dynamic world events such as natural disasters are oblique. These tasks are much more difficult for oblique images due to observed object parallax. There has been recent success in learning to regress geocentric pose, defined as height above ground and orientation with respect to gravity, by training with airborne lidar registered to satellite images. We present a model for this novel task that exploits affine invariance properties to outperform state of the art performance by a wide margin. We also address practical issues required to deploy this method in the wild for real-world applications. Our data and code are publicly available.