Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho ka Junming Chen

Moralo oa Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho ka Junming Chen ke mohlodi oa khau e hlomphehang haholo ya 2023 Moputso oa Tšepe oa A' Design Award Mokhahleong oa Tlhodisano oa Moralo wa Tlhahiso, Algorithimi, Paramethrike le AI.

TšepeTlhahiso· 2023

Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho

ka Junming Chen

Moreki: Chen junming

Mohlodi oa Moputso oa Tšepe oa A' Design Award Mokhahleong oa Tlhahiso

45,702

Mohlodi oa Khau ea Netefaditsweng

Netefatsa Boemo ba Khau bakeng sa #150834

Sheba ho A' Design Award Tokollo ya Boraditaba Baeche ya Moputso

Mebala

Moralo

Mabapi le Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho

Lefa la Theknoloji ke sesebediswa sa bohlale ba maiketsetso se hlahisang meralo ea ka ntle ho meaho. Sesebediswa sena se theha ponahalo ea meaho ka mefuta e fapaneng ea meralo ho tsoa mantsoeng a kentsoeng ke mosebedisi. Setšoantšo se seng le se seng se hlahisoa ka metsotsoana e seng mekae, 'me moralo o ka fetoloa ka ho fetola tlhaloso ea mantsoe. Sistimi ena e hahiloe ka ho bokella le ho beha lipehiso lisebelisoa tse likete tsa litšoantšo tsa boqapi ba meralo, kamora moo ho ntlafatsoa mmotlolo o seng o le teng oa ho hlahisa litšoantšo ka sete ena e ncha ea data. Sepheo ke ho thusa batho ba qalang ho fihlela boemo ba boleng ba porofešenale.

Kamohelo

Mabapi le Moputso oa Tšepe oa A' Design Award

Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho ke mohapi oa Moputso oa Tšepe oa A' Design Award, kananelo e hlomphehang e fuoang meralo e metle e finyellang litlhoko tsa porofeshenale le tsa indasteri tse lebelletsoeng ho lintho tse hlahisitsoeng tse entsoeng hantle. Bahapi ba Tšepe ba bontša bokhoni bo boholo, bokhethehi bo phahameng, kutloisiso ea litsebi le bokhoni ba boqapi ba baqapi ba bona. Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho e lebelletsoe ho ba ntho e hlahisitsoeng e hlomphuoang haholo, e ratoang le e ratehang, e sebetsang le e nang le mehopolo e mecha. Moralo ona o hapileng Moputso oa Tšepe oa A' Design Award o kenyelletsa mekhoa e metle ka ho fetesisa ea indasteri mme o na le litšobotsi tsa theknoloji tse nang le bokhoni tse amanang le tsebo le talenta. Ka lebaka la botlalo ba eona, Technology Inheritance Sesebediswa sa ho Theha Meralo ea Meaho e tšoanelehela tlhompho mme e entsoe ho fana ka ntlafatso ea bophelo e thusang ho etsa hore lefatše le be sebaka se molemo.

Ka Mora Moralo

Sete ya Boraditaba

Litlhaku, ditho tsa sehlopha le lintlha tsa botekgeniki tse fanoeng ke moetsi wa moralo.

Boleng bo Ikhethang: This project trains an AI that professionally generates the appearance of buildings. The AI can generate buildings of different architectural styles according to the text entered by the user. The AI only takes a few seconds to generate the building's appearance, and users can recreate the design by changing the text description. That is, designers can obtain design concept proposals through AI cooperation and continuously optimize the design.
Boholo le Phuthelo: Generating building exteriors using a fine-tuned stable diffusion technique.
Lithegi: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Theknoloji ya Tlhahiso: The effect of using stable diffusion to produce architectural appearance could be better. The reason is that this mode needs to sufficiently understand the design skills of different designers, resulting in a messy appearance design and low quality. For this, fine-tuning the existing AI is essential. So this project reworked the data set, fine-tuned the critical stable diffusion, and made an AI to generate the specified architectural style to assist the junior designer in the design.
Phephetso ya Moralo: The challenge of this design is to build a professional architectural design AI for generating high-quality and stylized designs. This project collected and marked thousands of architectural appearance renderings of dozens of well-known architects, created a data set of architectural appearance, and then handed the data set to AI for fine-tuning learning. This project builds an AI to generate a given building's exterior style.
Dipatlisiso: Research Background: It is difficult for beginners to design high-quality architectural appearances.
Methods: This project trained an AI to professionally generate building exteriors, which can contract with designers to complete architectural exterior designs.
Results: Using the AI trained in this project, the designer can generate an architectural appearance rendering in just a few seconds.
Insights: Using this method, the architectural appearance of a specified style can be generated and modified through text description, and the quality of the generated design is close to that of a professional designer. This method does not require manual modeling and rendering, which improves design efficiency and quality.
Kgothaletso: Most people measure the quality of a building by evaluating how it looks. Good architectural exterior design can bring attention and economic benefits. However, the exterior architectural design is complex, and the quality of architectural exteriors designed by excellent designers and beginners varies greatly. This design makes an artificial intelligence (AI) that can expertly generate building exteriors to help beginners achieve designs that approach the quality of master builders.
Nako ya Projeke: The project has already been completed in 2023.
Tsamaiso ya Mosebetsi: 1. Professional designers collect and mark, and screen images of outstanding designer building exteriors.
2. Use the filtered data to train an AI that specializes in generating the exterior of a given architectural style.
3. Designers use AI to design.
4. The designer inputs the design text description into the AI to specify the decoration style.
5. AI generates the interior design of the specified decoration style.
6. Modify the unsatisfactory details in the design through text description, and regenerate the design.
7. After adjusting the text description and generating it multiple times, a good design is obtained.