# Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction

arXiv: https://arxiv.org/abs/2107.03068 · HTML: https://mlsanity.com/paper/2107.03068/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 31 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [OpenVSLAM: A Versatile Visual SLAM Framework](https://mlsanity.com/paper/1910.01122/) (2019)
- [Scale Estimation of Monocular SfM for a Multi-modal Stereo Camera](https://mlsanity.com/paper/1810.11856/) (2018)
- [3D Pipe Network Reconstruction Based on Structure from Motion with Incremental Conic Shape Detection and Cylindrical Constraint](https://mlsanity.com/paper/2006.10383/) (2020)
- [VIO-Aided Structure from Motion Under Challenging Environments](https://mlsanity.com/paper/2101.09657/) (2021)

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

- [6D Camera Relocalization in Visually Ambiguous Extreme Environments](https://mlsanity.com/paper/2207.06333/) (2022)

## Abstract (arXiv)

In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection. To deal with peculiar appearances that hurt standard 3D reconstruction pipeline, we exploit pre-knowledge of the scene by selecting key frames in the sequence (called as anchors) which are roughly connected to a certain location. Our method then seek the location of each frame in time-order, while recursively updating an augmented 3D model which can provide current camera location and surrounding 3D structure. In an experiment on a practical industrial situation, our method can localize over 99% frames in the input sequence, whereas standard localization methods fail to reconstruct a complete camera trajectory.