English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visual place recognition is essential for vision-based robot localization andSLAM. Despite the tremendous progress made in recent years, place recognitionin changing environments remains challenging. A promising approach to cope withappearance variations is to leverage high-level semantic features like objectsor place categories. In this paper, we propose FM-Loc which is a novelimage-based localization approach based on Foundation Models that uses theLarge Language Model GPT-3 in combination with the Visual-Language Model CLIPto construct a semantic image descriptor that is robust to severe changes inscene geometry and camera viewpoint. We deploy CLIP to detect objects in animage, GPT-3 to suggest potential room labels based on the detected objects,and CLIP again to propose the most likely location label. The object labels andthe scene label constitute an image descriptor that we use to calculate asimilarity score between the query and database images. We validate ourapproach on real-world data that exhibit significant changes in cameraviewpoints and object placement between the database and query trajectories.The experimental results demonstrate that our method is applicable to a widerange of indoor scenarios without the need for training or fine-tuning.

FM-Loc: Using Foundation Models for Improved Vision-based Localization