VTechWorks staff will be away for the Thanksgiving holiday beginning at noon on Wednesday, November 27, through Friday, November 29. We will resume normal operations on Monday, December 2. Thank you for your patience.
 

Re_Imaged: Reimaging architecture through artificially intelligent generated images

Simple item page
dc.contributor.authorGajjar, Charmi Prafulen
dc.contributor.committeechairIshida, Akien
dc.contributor.committeememberBedford, Josephen
dc.contributor.committeememberBecker, Edward Gentryen
dc.contributor.committeememberHe, Chenxuanen
dc.contributor.departmentArchitectureen
dc.date.accessioned2023-07-28T08:04:48Zen
dc.date.available2023-07-28T08:04:48Zen
dc.date.issued2023-07-27en
dc.description.abstractArtificial Intelligence is a machine learning technique that exists everywhere in our day-to-day life. From a simple Google search that provides answers to any questions, to autocorrect suggestions provided while writing emails, we encounter AI in every next phase of our life. Humans have developed an invisible trust in AI that remains unrecognized. Artificial intelligence (AI) development in architecture has been a protracted and intriguing process. Recent advances in text-to-image generating software powered by AI have proven to be an efficient tool for architects to visualize their designs with a different perspective and enhance the thinking process. However, the lack of the tool's ability to capture the designer's integrity has shown the requirement for human involvement. This thesis claims that human decision-making skills remain crucial despite AI-augmented design's benefits. By conducting a comparative analysis between human-developed architecture and AI-augmented designs through the process of AI text-to-image generating tool Stable Diffusion, the thesis argues that human brain involvement is necessary due to the lack of Stable Diffusion's ability to understand architectural drawings and elements, the ability to representing architectural depth through spaces and emotions, and its inadequate learning from the past design experiences.en
dc.description.abstractgeneralHuman communication has mainly based on gestures and visuals before the advent of writing and widespread literacy. Images have been one of the successful means of transiting design ideas. Past and present works of art have influenced the process of design thinking for architects. The human mind has always been able to capture past experiences and memories in the form of a collective database to convey new ideas. An average human brain can store up to 2.5 million gigabytes of memory. Artificial Intelligence is a computer language system that operates similarly to the human thinking process. The machine can learn from infinite gathered past data and provide exceptional results every time. It refers to developing intelligent computer systems that can mimic human problem-solving ability to an extent. With the active emergence of Artificial intelligence in the 21st century, there has been a rise in interest in generating realistic images by translating written descriptions. Through collaboration with human thinking processes and AI-generated images, designers can discover an additional tool to communicate their ideas. This thesis aims to summarize the evolution of AI in architecture and explore the potential use of text-to-image and image-to-image generating tools to transform the architectural design process.en
dc.description.degreeMaster of Architectureen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:37892en
dc.identifier.urihttp://hdl.handle.net/10919/115901en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectartificial intelligenceen
dc.subjectimagesen
dc.subjectarchitectureen
dc.subjectdigitalen
dc.subjecttechnologyen
dc.subjectpixelsen
dc.titleRe_Imaged: Reimaging architecture through artificially intelligent generated imagesen
dc.typeThesisen
thesis.degree.disciplineArchitectureen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Architectureen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Gajjar_CP_T_2023.pdf
Size:
31.06 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses