# DeepCompass: AI-driven Location-Orientation Synchronization for Navigating Platforms

arXiv: https://arxiv.org/abs/2311.12805 · HTML: https://mlsanity.com/paper/2311.12805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 15 Sep 2023.

## Builds on (most cited first, 13 of 13)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime](https://mlsanity.com/paper/1810.02575/) (2018)
- [OrienterNet: Visual Localization in 2D Public Maps with Neural Matching](https://mlsanity.com/paper/2304.02009/) (2023)
- [Night-to-Day Image Translation for Retrieval-based Localization](https://mlsanity.com/paper/1809.09767/) (2018)
- [SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation](https://mlsanity.com/paper/2211.14651/) (2022)
- [SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving](https://mlsanity.com/paper/2106.11118/) (2021)
- [Magnetometer calibration using inertial sensors](https://mlsanity.com/paper/1601.05257/) (2016)
- [On Calibration of Three-axis Magnetometer](https://mlsanity.com/paper/1509.02046/) (2015)
- [Dynamic Magnetometer Calibration and Alignment to Inertial Sensors by Kalman Filtering](https://mlsanity.com/paper/1612.01044/) (2016)
- [Place Recognition under Occlusion and Changing Appearance via Disentangled Representations](https://mlsanity.com/paper/2211.11439/) (2022)

## Abstract (arXiv)

In current navigating platforms, the user's orientation is typically estimated based on the difference between two consecutive locations. In other words, the orientation cannot be identified until the second location is taken. This asynchronous location-orientation identification often leads to our real-life question: Why does my navigator tell the wrong direction of my car at the beginning? We propose DeepCompass to identify the user's orientation by bridging the gap between the street-view and the user-view images. First, we explore suitable model architectures and design corresponding input configuration. Second, we demonstrate artificial transformation techniques (e.g., style transfer and road segmentation) to minimize the disparity between the street-view and the user's real-time experience. We evaluate DeepCompass with extensive evaluation in various driving conditions. DeepCompass does not require additional hardware and is also not susceptible to external interference, in contrast to magnetometer-based navigator. This highlights the potential of DeepCompass as an add-on to existing sensor-based orientation detection methods.