Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo ngu-Junming Chen

Umdwebo Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo ngu-Junming Chen ungumnqobi ohlonishwa kakhulu womklomelo odumile we-2023 Umklomelo Wensimbi we-A' Design Award Esigabeni Somncintiswano se-Okuzenzakalelayo.

InsimbiOkuzenzakalelayo· 2023

Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo

ngu Junming Chen

Iklayenti: Chen junming

Umnqobi we-Umklomelo Wensimbi we-A' Design Award Esigabeni se-Okuzenzakalelayo

45,702

Umnqobi Womklomelo Oqinisekisiwe

Qinisekisa Isimo Somklomelo se-#150834

Buka ku-A' Design Award Isitatimende Sabezindaba Ibheji Yomklomelo

Imibala

Ukuklama

Mayelana ne-Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo

Ifa Lobuchwepheshe liyithuluzi lobuhlakani bokwenziwa (artificial intelligence) elidala imiklamo yangaphandle yezakhiwo. Leli thuluzi lidala izinhlobo zezakhiwo ezitshengisa izitayela ezahlukene zokwakha ngokususela embhalweni ofakwe umsebenzisi. Isithombe ngasinye sikhiqizwa ngemizuzwana embalwa, futhi umklamo ungashintshwa ngokuhlela incazelo yombhalo. Le sistimu yakhiwa ngokuqoqa nokufaka izimpawu ezinkulungwaneni zezithombe zezakhiwo ezidwetshiwe, kwabe sekuthuthukiswa imodeli ekhona yokukhiqiza izithombe ngalolu hlu olusha lwedatha. Inhloso ukusiza abaqalayo bafinyelele izinga lekhwalithi elingokwesigaba sochwepheshe.

Ukuqashelwa

Mayelana ne-Umklomelo Wensimbi we-A' Design Award

Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo iwinile uMklomelo Wensimbi we-A' Design Award, ukwaziswa okuhloniphekile okunikezwa imiklamo emihle ehlangabezana nezidingo zobungcweti nezemboni ezilindelekile ezimpahleni ezihlelwe kahle. Abawinile beNsimbi babonisa ikhono elikhulu, ubungcweti obuphezulu, ukuqonda kochwepheshe namandla okudala abadali babo. Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo ilindeleke ukuba ibe yinto exatshwa kakhulu, edunyiswayo nethandwayo esebenzayo nenezinto ezintsha. Lo mklamo owinile uMklomelo Wensimbi we-A' Design Award uhlanganisa izindlela ezinhle kakhulu zemboni futhi unezimfanelo zobuchwepheshe ezifanelekile ezihlanganiswe nolwazi nethalente. Technology Inheritance Ithuluzi Lokudala Ukwakhiwa Kwezakhiwo iyahlonishwa ngenxa yokucophelela kwayo futhi ihlelelwe ukulethela izinguquko zomgangatho wempilo ezisiza ukwenza umhlaba ube yindawo engcono.

Ngemuva Kokuklama

Iphakheji Yabezindaba

Ama-credit, amalungu eqembu nemininingwane yobuchwepheshe ehlinzekwe ngumklami.

Izici Ezihlukile: 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.
Izilinganiso Nokupakisha: Generating building exteriors using a fine-tuned stable diffusion technique.
Amathegi: Artificial intelligence, Human-computer cooperation, Architectural appearance generation, Text generation design, Quick modification, Architectural style control
Ubuchwepheshe Bokukhiqiza: 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.
Inselele Yokudweba: 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.
Ucwaningo: 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.
Ugqozi: 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.
Ubude Bephrojekthi: The project has already been completed in 2023.
Ukuhamba Kokusebenza: 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.