Research areas
Here we bring together the research directions NexCo is exploring. Each overview describes how the technology works, the application settings under consideration and the tests needed to assess its feasibility and usefulness.
When a research direction moves into prototyping or produces verifiable results, we will publish the method, metrics and progress.
How to read the archive
Archive
4 items
Digital spaces and positioning
We study how to reconstruct a navigable representation of a space from images captured from multiple viewpoints.
How far can the time and manual work needed to digitise a real place be reduced while maintaining visual quality and usability suitable for commercial use?
Digital spaces and positioning
We explore systems that compare images captured by a device with a visual map of the space to estimate its position and orientation.
In which environments and conditions can a visual map provide sufficiently reliable positioning to support navigation, augmented reality or autonomous systems?
AI and data systems
We study how to recognise objects, interpret scenes and extract information from images and video to support real-world processes and applications.
How can images and video be turned into reliable information useful to a real process, even when lighting, viewpoint and capture conditions change?
AI and data systems
We study the architecture of a software layer external to language models, designed to determine which information to retain, update and retrieve.
How can useful memory be built across sessions without turning incorrect, outdated or unauthorised information into seemingly reliable context?