# Addressing Challenging Place Recognition Tasks using Generative Adversarial Networks

arXiv: https://arxiv.org/abs/1709.08810 · HTML: https://mlsanity.com/paper/1709.08810/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2017.

## Built on by (most cited first, 9 of 9)

- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [A Hierarchical Dual Model of Environment- and Place-Specific Utility for Visual Place Recognition](https://mlsanity.com/paper/2107.02440/) (2021)
- [MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery](https://mlsanity.com/paper/2202.09146/) (2022)
- [Place recognition survey: An update on deep learning approaches](https://mlsanity.com/paper/2106.10458/) (2021)
- [BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition](https://mlsanity.com/paper/2208.14543/) (2022)
- [PlaceNav: Topological Navigation through Place Recognition](https://mlsanity.com/paper/2309.17260/) (2023)
- [Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning](https://mlsanity.com/paper/2102.04960/) (2021)
- [Co-visual pattern augmented generative transformer learning for automobile geo-localization](https://mlsanity.com/paper/2203.09135/) (2022)

## Abstract (arXiv)

Place recognition is an essential component of Simultaneous Localization And Mapping (SLAM). Under severe appearance change, reliable place recognition is a difficult perception task since the same place is perceptually very different in the morning, at night, or over different seasons. This work addresses place recognition as a domain translation task. Using a pair of coupled Generative Adversarial Networks (GANs), we show that it is possible to generate the appearance of one domain (such as summer) from another (such as winter) without requiring image-to-image correspondences across the domains. Mapping between domains is learned from sets of images in each domain without knowing the instance-to-instance correspondence by enforcing a cyclic consistency constraint. In the process, meaningful feature spaces are learned for each domain, the distances in which can be used for the task of place recognition. Experiments show that learned features correspond to visual similarity and can be effectively used for place recognition across seasons.