# PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization

arXiv: https://arxiv.org/abs/1505.07427 · HTML: https://mlsanity.com/paper/1505.07427/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2015.

## Built on by (most cited first, 11 of 11)

- [nerf2nerf: Pairwise Registration of Neural Radiance Fields](https://mlsanity.com/paper/2211.01600/) (2022)
- [Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization](https://mlsanity.com/paper/2202.01821/) (2022)
- [BroadTrack: Broadcast Camera Tracking for Soccer](https://mlsanity.com/paper/2412.01721/) (2024)
- [Mono-hydra: Real-time 3D scene graph construction from monocular camera input with IMU](https://mlsanity.com/paper/2308.05515/) (2023)
- [Self-Supervised Feature Learning for Long-Term Metric Visual Localization](https://mlsanity.com/paper/2212.00122/) (2022)
- [PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis](https://mlsanity.com/paper/2510.19527/) (2025)
- [Visual Relocalization from Sparse Views in Aliased and Low-Texture Environments via Novel View Synthesis](https://mlsanity.com/paper/2607.22147/) (2026)
- [A Novel Three-Dimensional Navigation Method for the Visually Impaired](https://mlsanity.com/paper/2206.11136/) (2022)
- [Neural Camera Models](https://mlsanity.com/paper/2208.12903/) (2022)
- [Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis](https://mlsanity.com/paper/2501.07221/) (2025)
- [Robust PnP on a Neuromorphic Processor for Object Pose Estimation](https://mlsanity.com/paper/2607.16834/) (2026)

## Abstract (arXiv)

We present a robust and real-time monocular six degree of freedom relocalization system. Our system trains a convolutional neural network to regress the 6-DOF camera pose from a single RGB image in an end-to-end manner with no need of additional engineering or graph optimisation. The algorithm can operate indoors and outdoors in real time, taking 5ms per frame to compute. It obtains approximately 2m and 6 degree accuracy for large scale outdoor scenes and 0.5m and 10 degree accuracy indoors. This is achieved using an efficient 23 layer deep convnet, demonstrating that convnets can be used to solve complicated out of image plane regression problems. This was made possible by leveraging transfer learning from large scale classification data. We show the convnet localizes from high level features and is robust to difficult lighting, motion blur and different camera intrinsics where point based SIFT registration fails. Furthermore we show how the pose feature that is produced generalizes to other scenes allowing us to regress pose with only a few dozen training examples. PoseNet code, dataset and an online demonstration is available on our project webpage, at http://mi.eng.cam.ac.uk/projects/relocalisation/