# 3D Reconstruction from public webcams

arXiv: https://arxiv.org/abs/2108.09476 · HTML: https://mlsanity.com/paper/2108.09476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 21 Aug 2021.

## Builds on (most cited first, 14 of 14)

- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Image Matching across Wide Baselines: From Paper to Practice](https://mlsanity.com/paper/2003.01587/) (2020)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [MAGSAC: marginalizing sample consensus](https://mlsanity.com/paper/1803.07469/) (2018)
- [Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking](https://mlsanity.com/paper/2007.14557/) (2020)
- [Deep Cosine Metric Learning for Person Re-Identification](https://mlsanity.com/paper/1812.00442/) (2018)
- [Discriminative Correlation Filter with Channel and Spatial Reliability](https://mlsanity.com/paper/1611.08461/) (2016)
- [MODS: Fast and Robust Method for Two-View Matching](https://mlsanity.com/paper/1503.02619/) (2015)
- [Minimal Solvers for Single-View Lens-Distorted Camera Auto-Calibration](https://mlsanity.com/paper/2011.08988/) (2020)
- [Reconstruction of 3D flight trajectories from ad-hoc camera networks](https://mlsanity.com/paper/2003.04784/) (2020)
- [On the Two-View Geometry of Unsynchronized Cameras](https://mlsanity.com/paper/1704.06843/) (2017)
- [Minimal Solvers for Rectifying from Radially-Distorted Conjugate Translations](https://mlsanity.com/paper/1911.01507/) (2019)

## Abstract (arXiv)

We investigate the possibility of 3D scene reconstruction from two or more overlapping webcam streams. A large, and growing, number of webcams observe places of interest and are publicly accessible. The question naturally arises: can we make use of this free data source for 3D computer vision? It turns out that the task to reconstruct scene structure from webcam streams is very different from standard structure-from-motion (SfM), and conventional SfM pipelines fail. In the webcam setting there are very few views of the same scene, in most cases only the minimum of two. These viewpoints often have large baselines and/or scale differences, their overlap is rather limited, and besides unknown internal and external calibration also their temporal synchronisation is unknown. On the other hand, they record rather large fields of view continuously over long time spans, so that they regularly observe dynamic objects moving through the scene. We show how to leverage recent advances in several areas of computer vision to adapt SfM reconstruction to this particular scenario and reconstruct the unknown camera poses, the 3D scene structure, and the 3D trajectories of dynamic objects.