mlsanityData to 7 Oct 2026

Single View Geocentric Pose in the Wild

arXiv 2105.08229 ↗First posted 18 May 2021cs.CVcited by 9

Not on the map. Why?

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.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 18 of its 45 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

18 of 45 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  5. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  6. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  7. 2018DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Imagescited by 276
  8. 2014Learning Rich Features from RGB-D Images for Object Detection and Segmentationcited by 124
  9. 2018Depth-aware CNN for RGB-D Segmentationcited by 73
  10. 2019Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationcited by 61
  11. 2018Semantic Stereo for Incidental Satellite Imagescited by 53
  12. 2018IM2HEIGHT: Height Estimation from Single Monocular Imagery via Fully Residual Convolutional-Deconvolutional Networkcited by 31
6 more
  1. 2019SpaceNet MVOI: a Multi-View Overhead Imagery Datasetcited by 29
  2. 2019Leveraging Vision Reconstruction Pipelines for Satellite Imagerycited by 23
  3. 2018RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Cluttercited by 21
  4. 2020Learning Geocentric Object Pose in Oblique Monocular Imagescited by 16
  5. 2018From Satellite Imagery to Disaster Insightscited by 9
  6. 2019AutoCorrect: Deep Inductive Alignment of Noisy Geometric Annotationscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 2; 2025: 1.

9 papers.

  1. 20243D Building Reconstruction from Monocular Remote Sensing Images with Multi-level Supervisionscited by 12
  2. 2024SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagerycited by 9
  3. 2021THE Benchmark: Transferable Representation Learning for Monocular Height Estimationcited by 8
  4. 2023HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Imagescited by 8
  5. 2025Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervisioncited by 6
  6. 2022Disentangled Latent Transformer for Interpretable Monocular Height Estimationcited by 3
  7. 2022Handling Image and Label Resolution Mismatch in Remote Sensingcited by 3
  8. 2022A Deep Learning Ensemble Framework for Off-Nadir Geocentric Pose Predictioncited by 0
  9. 2023Impact of architecture on robustness and interpretability of multispectral deep neural networkscited by 0