Using street view images and visual LLMs to predict heritage values for governance support: Risks, ethics, and policy implications
arXiv:2601.06056v2 Announce Type: replace-cross Abstract: During 2025 and 2026, the Energy Performance of Buildings Directive is being implemented in the European Union member states, requiring all member states to have National Building Renovation Plans. In Sweden, there is no comprehensive national register of buildings with heritage values. This is seen as a barrier for the analyses underlying the development of Building Renovation Plans by the involved Swedish authorities. The purpose of this research was to assist Swedish authorities in developing information on heritage values in the Swe
The implementation of the Energy Performance of Buildings Directive in the EU creates an immediate need for better data on heritage values to develop National Building Renovation Plans.
Authorities are using visual LLMs and street view images to gain insights into urban environments and heritage planning, demonstrating AI's growing role in governance and policy support.
The previous barrier of a lack of comprehensive national registers for heritage values can now be addressed more efficiently through AI-powered visual analysis, improving urban planning data.
- · Swedish authorities
- · Urban planners
- · AI/LLM developers
- · Environmental governance
- · Traditional manual survey methods
- · Bureaucracies reliant on incomplete data
AI-driven visual analysis significantly speeds up the identification and cataloging of heritage buildings.
Improved heritage data leads to more effective and targeted building renovation plans, potentially preserving cultural assets while meeting energy efficiency goals.
The success of this approach in Sweden could spur further adoption of visual LLMs for diverse urban planning and regulatory tasks across the EU and globally, enhancing 'smart' governance capabilities.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI