
Digital design technologies are currently dominating visual communications in the field of landscape architecture. Due to rapid technological changes, artificial intelligence (AI) graphic software appears to be the next frontier in creating digital imagery, though little is known on the potential of artificial intelligence for rendering landscape architecture graphics. The objective of this study is to determine the effectiveness and efficiencies of current Adobe-based rendering techniques, such as digital collaging in Photoshop, compared with the two major types of AI visualization software: text-based image generation (DALL-E 2) and sketch-based image refinement (NVIDIA GauGAN2). Images produced by current methods and AI software were evaluated by landscape architecture professionals. Professionals were also surveyed on their attitudes toward and adoption of AI programs. This study aims to determine whether AI-based software can compete with visualization methods currently taught to landscape architecture students and used by landscape architecture professionals. Understanding and adoption of AI-based visualization techniques may lead to significant changes in landscape architectural practice and education.
Autor / Author: | Li, Marika; Amoroso, Nadia |
Institution / Institution: | University of Guelph, Ontario/Canada; University of Guelph, Ontario/Canada |
Seitenzahl / Pages: | 11 |
Sprache / Language: | Englisch |
Veröffentlichung / Publication: | JoDLA – Journal of Digital Landscape Architecture, 8-2023 |
Tagung / Conference: | Digital Landscape Architecture 2023 – Future Resilient Landscapes |
Veranstaltungsort, -datum / Venue, Date: | Dessau Campus of Anhalt University, Germany 24-05-23 - 27-05-23 |
Schlüsselwörter (de): | |
Keywords (en): | Digital landscapes, visual communications, text-to-image, landscape software |
Paper review type: | Full Paper Review |
DOI: | doi:10.14627/537740057 |
Diese Website nutzt Cookies, um ihre Dienste anbieten zu können und Zugriffe zu analysieren. Dabei ist uns der Datenschutz sehr wichtig.
Legen Sie hier Ihre Cookie-Einstellungen fest. Sie können Sie jederzeit auf der Seite Cookie-Informationen ändern.