Thesis (M.F.A.)--Rochester Institute of Technology, 2008. / Typescript. Includes bibliographical references (leaf 19).

The rising cost in video game content creation, both in terms of man hours and in terms of monetary dollars, restricts the ability of video game developers to create unique, entertaining content. Motivated by how this cost is a direct result of "next-generation graphics", I am motivated to ask: what would a next-generation content creation tool look like? I investigate the problem by constructing several such tools. In particular, I construct a mesh quilting algorithm for random level generation, a rapid level construction toolkit based on the concept of an architectural blueprint but supporting features such as complex silhouette geometry and roof geometry, and a tool for rapidly painting world textures. I also introduce a new system for accessing barycentric coordinate data from within the fragment shader, which can be used in support of real-time 3D image quilting, more accurate normal interpolation, and texture rendering from within the world painting tool. Some history of video game content creation is discussed, and a roadmap is charted for future development. / Graduate

AI-generativa bildkonst verktyg använder sig av generative adversarial networks (GAN) för att skapa bilder. Generative adversarial networks blir desto bättre ju mer information den förses med. Denna studie undersöker hur teknologiskt accepterat det är med AI-genererade bildkonst verktyg med hjälp av modellen Technology Acceptance Model (TAM). Syftet med studien är att undersöka om unga konstnärers syn och inställning på AI-genererad bildkonst och verktygets framfart samt om de anser att det är accepterat. Studien genomfördes med små n-studier med semistrukturerade intervjuer för att få en rik och detaljerad beskrivning om acceptansen kring AI-generativa bildkonst verktyg. Studiens intervjufrågor byggdes upp för att besvara TAM2s olika delar. Respondenterna var konstnärer från Sverige och valdes ut genom bekvämlighetsurval kombinerat med snowball sampling. Konstnärerna som intervjuades under studien var positivt inställda till att använda AI-bildverktygen som inspiration och hjälpmedel till deras egna konst, och de flesta konstnärerna ansåg inte att AI var ett hot för dem eftersom de höll på med fysiska konstverk, och såg AI mer som ett hot för digitala konstnärer. Dessutom tyckte de flesta konstnärerna i studien att även om det är en själv som har skrivit in instruktionerna till AI-bildverktygen för att få en genererad bild, så är det diskutabelt om man kan göra anspråk på verket. / AI generated visual art tools use generative adversarial networks (GAN) to create pictures and digital art. Generative adversarial networks get better the more information they are provided with. This study investigates how technologically accepted it is with AI generated visual art tools using the Technology Acceptance Model (TAM). This study was carried out with small n-studies with semi-structured interviews to get rich and detailed description of the acceptance of AI generative visual art tools. The study’s interview questions were built to answer the TAM2-model different parts. The respondents were artists from Sweden and were selected through convenience sampling combined with snowball sampling. The purpose of the study is to investigate how young artists view and attitude towards AI generated visual art and the progress of the tool and whether they believe it is accepted. The artists interviewed during the study were positive about using the AI generated art tool as an inspiration and aid to their own art, and most of the artists did not consider AI as a threat to them because they were doing physical artwork, seeing AI more as a threat to digital artists. In addition, most of the artists in the study felt that even if one has entered the instructions to the AI generating tools themselves to get a generated image, it is debatable whether one can claim the work. This thesis is written in Swedish.